NA
Uploaded byNazir Ahmed
PPTX, PDF1,885 views

Artificial intelligence(03)

An intelligent agent is an entity that is situated in an environment, autonomous, and flexible. It perceives its environment through sensors and acts upon the environment through effectors. There are different types of agents including simple reflex agents, model-based reflex agents, goal-based agents, and utility-based agents. Environments can be fully or partially observable, deterministic or stochastic, static or dynamic, discrete or continuous, and involve a single agent or multiple agents. Examples of environments include chess, poker, backgammon, taxi driving, medical diagnosis, and image analysis.

Educationâ—Ļ

Embed presentation

Download to read offline
Artificial Intelligence
What is an Intelligent agent? â€ĸ “Agent” can be considered as a theoretical concept from AI. â€ĸ Many different definitions exist in the literatureâ€Ļ..
Agent Definition (1) â€ĸ An agent is an entity which is: – Situated in some environment. – Autonomous, in the sense that it can act without direct intervention from humans or other software processes, and controls over its own actions and internal state. – Flexible which means: â€ĸ Responsive (reactive): agents should perceive their environment and respond to changes that occur in it; â€ĸ Proactive: agents should not simply act in response to their environment, they should be able to exhibit opportunistic, goal-directed behavior and take the initiative when appropriate; â€ĸ Social: agents should be able to interact with humans or other artificial agents
Agent Definition (2) American Heritage Dictionary: agent- ” â€Ļ one that acts or has the power or authority to actâ€Ļ or represent another”
â€ĸ "An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors." Russell & Norvig Agent Definition (3)
“Intelligent agents continuously perform three functions: â€ĸ perception of dynamic conditions in the environment; â€ĸ action to affect conditions in the environment; and â€ĸ reasoning to interpret perceptions, solve problems, draw inferences, and determine actions.” Barbara Hayes-Roth Agent Definition (5)
Agents & Environments īą The agent takes sensory input from its environment, and produces as output actions that affect it. Environment sensor input action outputAgent
Internal and External Environment of an Agent Internal Environment: architecture, goals, abilities, sensors, effectors, profile, knowledge, beliefs, etc. External Environment: user, other humans, other agents, applications, information sources, their relationships, platforms, servers, networks, etc. Balance
Overall Intelligent Agent [Terziyan, 1993] 1) is goal-oriented, because it should have at least one goal - to keep continuously balance between its internal and external environments ; 2) is creative because of the ability to change external environment; 3) is adaptive because of the ability to change internal environment; 4) is mobile because of the ability to move to another place; 5) is social because of the ability to communicate to create a community; 6) is self-configurable because of the ability to protect “mental health” by sensing only a “suitable” part of the environment.
Agent Definition Wikipedia: (The free Encyclopedia), īąIn computer science, an intelligent agent (IA) is a software agent that exhibits some form of artificial intelligence that assists the user and will act on their behalf, in performing non-repetitive computer- related tasks. īąWhile the working of software agents used for operator assistance or data mining is often based on fixed pre-programmed rules, "intelligent" here implies the ability to adapt and learn.
Three groups of agents [Etzioni and Daniel S. Weld, 1995] â€ĸ Backseat driver: helps the user during some task (e.g., Microsoft Office Assistant); â€ĸ Taxi driver: knows where to go when you tell the destination; â€ĸ Caretaker : know where to go, when and why.
Agent’s function maps â€ĸ The agent function maps from percept histories to actions:
Agents example â€ĸ Human agent: – eyes, ears, and other organs for sensors; – hands, legs, mouth, and other body parts for actuators â€ĸ Robotic agent: – cameras and infrared range finders for sensors – various motors for actuators
PEAS â€ĸ Use PEAS to describe task environment – Performance measure – Environment – Actuators – Sensors â€ĸ Example: Taxi driver – Performance measure: safe, fast, comfortable (maximize profits) – Environment: roads, other traffic, pedestrians, customers – Actuators: steering, accelerator, brake, signal, horn – Sensors: cameras, sonar, speedometer, GPS, odometer, accelerometer, engine sensors
PEAS â€ĸ Agent: Part-picking robot â€ĸ Performance measure: Percentage of parts in correct bins â€ĸ Environment: Conveyor belt with parts, bins â€ĸ Actuators: Jointed arm and hand â€ĸ Sensors: Camera, joint angle sensors
PEAS â€ĸ Agent: Medical diagnosis system â€ĸ Performance measure: Healthy patient, minimize costs, lawsuits â€ĸ Environment: Patient, hospital, staff â€ĸ Actuators: Screen display (questions, tests, diagnoses, treatments, referrals) â€ĸ â€ĸ Sensors: Keyboard (entry of symptoms, findings, patient's answers)
PEAS â€ĸ Agent: Interactive English tutor â€ĸ Performance measure: Maximize student's score on test â€ĸ Environment: Set of students â€ĸ Actuators: Screen display (exercises, suggestions, corrections) â€ĸ Sensors: Keyboard
Description of Agent‘s character īą An agent is responsible for satisfying specific goals. There can be different types of goals such as achieving a specific status, maximising a given function (e.g., utility), etc. īą The state of an agent includes state of its internal environment + state of knowledge and beliefs about its external environment. knowledge beliefs Goal1 Goal2
Connections â€ĸ An agent is situated in an environment, that consists of the objects and other agents it is possible to interact with. â€ĸ An agent has an identity that distinguishes it from the other agents of its environment. environment
Agent types â€ĸ Four basic types in order of increasing generalization: – Simple reflex agents – Reflex agents with state/model – Goal-based agents – Utility-based agents
Simple Reflex Agent ī‚ĸ Instead of specifying individual mappings in an explicit table, common input-output associations are recorded ī‚— Requires processing of percepts to achieve some abstraction ī‚— Frequent method of specification is through condition-action rules ī‚ĸ if percept then action ī‚ĸ If car-in-front-is-braking then initiate-braking ī‚— Similar to innate reflexes or learned responses in humans ī‚— Efficient implementation, but limited power ī‚ĸ Environment must be fully observable ī‚ĸ Easily runs into infinite loops
Simple reflex agents
Simple Reflex Agent â€ĸ function SIMPLE-REFLEX-AGENT (percept) returns action – static: rules, a set of condition-action rules – state ← INTERPRET-INPUT (percept) – rule ← RULE-MATCH (state, rules) – action ← RULE-ACTION [rule] – return action
A simple reflex agent.. â€ĸ which works by finding a rule whose condition matches the current situation and then doing the action associated with that rule
Reflex agents with state/model â€ĸ Evan a little bit of un observability can cause serious trouble. – The braking rule given earlier assumes that the condition car-in-front-is-braking can be determined from the current percept – the current video image. â€ĸ More advanced techniques would require the maintenance of some kind of internal state to choose an action.
Reflex agents with state/model ī‚ĸ An internal state maintains important information from previous percepts ī‚— Sensors only provide a partial picture of the environment ī‚— Helps with some partially observable environments ī‚ĸ The internal states reflects the agent’s knowledge about the world ī‚— This knowledge is called a model ī‚— May contain information about changes in the world
Model-based reflex agents â€ĸ Required information: – How the world evolves independently of the agent? â€ĸ An overtaking car generally will be closer behind than it was a moment ago. â€ĸ The current percept is combined with the old internal state to generate the updated description of the current state.
Model-based reflex agents
Model-based reflex agents â€ĸ function REFLEX-AGENT-WITH-STATE (percept) returns an action – static: state, a description of the current world state rules, a set of condition-action rules action, the most recent action, initially none – state ← UPDATE-STATE (state, action, percept) – rule ← RULE-MATCH (state, rules) – action ← RULE-ACTION [rule] – state ← UPDATE-STATE (state, action) – return action
Goal-based agent â€ĸ Merely knowing about the current state of the environment is not always enough to decide what to do next. â€ĸ The right decision depends on where the taxi is trying to get to. â€ĸ So the goal information is also needed.
Goal-based agent â€ĸ Goal-based agents are far more flexible. – If it starts to rain, the agent adjusts itself to the changed circumstances, since it also looks at the way its actions would affect its goals (remember doing the right thing). – For the reflex agent we would have to rewrite a large number of condition-action rules.
Goal-based agents
Utility-based agents â€ĸ Goals are not really enough to generate high- quality behavior. â€ĸ There are many ways to reach the destination, but some are qualitatively better than others. – More safe – Shorter – Less expensive
Utility-based agent â€ĸ We say that if one world state is preferred to another, then it has higher utility for the agent. â€ĸ Utility is a function that maps a state onto a real number. – state → R â€ĸ Any rational agent possesses a utility function.
Utility-based agents
Environments â€ĸ Actions are done by the agent on the environment. â€ĸ Environment provides percepts to the agent. â€ĸ Determine to a large degree the interaction between the “outside world” and the agent – the “outside world” is not necessarily the “real world” as we perceive it â€ĸ it may be a real or virtual environment the agent lives in â€ĸ In many cases, environments are implemented within computers – They may or may not have a close correspondence to the “real world”
Properties of environments â€ĸ Fully observable vs. partially observable â€ĸ Or Accessible vs. inaccessible – If an agent’s sensory equipment gives it access to the complete state of the environment, then we say that environment is fully observable to the agent. – An environment is effectively fully observable if the sensors detect all aspects that are relevant to the choice of action. – A fully observable environment is convenient because the agent need not maintain any internal state to keep track of the world.
Properties of environments â€ĸ Deterministic vs. nondeterministic. – If the next state of the environment is completely determined by the current state and the actions selected by the agents, then we say the environment is deterministic. – If the environment is inaccessible, then it may appear to be nondeterministic (bunch of uncertainties).
Properties of task environments â€ĸ Episodic vs. sequential. – Agent’s experience is divided into “episodes.” â€ĸ Each episode consists of the agent perceiving and acting. – Subsequent episodes do not depend on what actions occur in previous episodes. – In sequential environments current actions affect all succeeding actions
Properties of task environments â€ĸ Static vs. Dynamic – If the environment can change while an agent is performing action, then we say the environment is dynamic. – Else its static. – Static environments are easy to deal with, because the agent does not keep on looking at the environment while it is deciding on an action. – Semidynamic: if the environment does not change with the passage of time but the agent performance score does.
Properties of environments â€ĸ Discrete vs. continuous – If there are a limited number of distinct, clearly defined percepts and actions, we say that the environment is discrete. â€ĸ Chess, since there are a fixed number of possible moves on each turn. â€ĸ Taxi driving is continuous.
Properties of environments â€ĸ Single agent vs. Multiagent – In the single agent environment there is only one agent â€ĸ A computer software playing crossword puzzle – In multiagent systems, there are more than one active agents â€ĸ Video games
Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Chess without a clock Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent EnvironmentExamples
EnvironmentExamples Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis
Environment Examples Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking Fully Determi nistic Episodic Semi Discrete Single
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking Fully Determi nistic Episodic Semi Discrete Single Interactive English tutor
Environment Examples Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking Fully Determi nistic Episodic Semi Discrete Single Interactive English tutor Partial Stochast ic Sequential Dyna mic Discrete Multi

More Related Content

PPTX
AI Agents, Agents in Artificial Intelligence
byKirti Verma
 
PPTX
Adversarial search with Game Playing
byAman Patel
 
PPTX
AI_Session 10 Local search in continious space.pptx
byGuru Nanak Technical Institutions
 
PPT
AI Lecture 3 (solving problems by searching)
byTajim Md. Niamat Ullah Akhund
 
PPTX
Artificial Intelligence
byVinod Kumar Meghwar
 
PPTX
Deep Reinforcement Learning
byUsman Qayyum
 
PPT
Lecture 11 Informed Search
byHema Kashyap
 
PPTX
Fuzzy logic and application in AI
byIldar Nurgaliev
 
AI Agents, Agents in Artificial Intelligence
byKirti Verma
 
Adversarial search with Game Playing
byAman Patel
 
AI_Session 10 Local search in continious space.pptx
byGuru Nanak Technical Institutions
 
AI Lecture 3 (solving problems by searching)
byTajim Md. Niamat Ullah Akhund
 
Artificial Intelligence
byVinod Kumar Meghwar
 
Deep Reinforcement Learning
byUsman Qayyum
 
Lecture 11 Informed Search
byHema Kashyap
 
Fuzzy logic and application in AI
byIldar Nurgaliev
 

What's hot

PPT
BackTracking Algorithm: Technique and Examples
byFahim Ferdous
 
PPTX
Problem solving agents
byMegha Sharma
 
PDF
Lecture 2 agent and environment
byVajira Thambawita
 
PPTX
Intelligent agent
byGeeta Jaswani
 
PPTX
Constraint satisfaction problems (csp)
byArchana432045
 
PDF
I.BEST FIRST SEARCH IN AI
byvikas dhakane
 
PDF
Informed search
byAmit Kumar Rathi
 
PPTX
intelligent agent (1).pptx
byShivareddyGangam
 
PPTX
Learning in AI
byMinakshi Atre
 
PPTX
asymptotic notation
bySangeethaSasi1
 
PPTX
Implementation of lexical analyser
byArchana Gopinath
 
PPTX
Adversarial search
byNilu Desai
 
PPT
Searching
byProf.Dharmishtha R. Chaudhari
 
PPT
Bayseian decision theory
bysia16
 
PPTX
Reinforcement learning
byDing Li
 
PPT
AI Lecture 2 (intelligent agents)
byTajim Md. Niamat Ullah Akhund
 
PDF
Ch 7 Knowledge Representation.pdf
byKrishnaMadala1
 
PPTX
Adversarial Search
byMegha Sharma
 
PPTX
Hill climbing algorithm
byDr. C.V. Suresh Babu
 
PPTX
Informed search algorithms.pptx
byDr.Shweta
 
BackTracking Algorithm: Technique and Examples
byFahim Ferdous
 
Problem solving agents
byMegha Sharma
 
Lecture 2 agent and environment
byVajira Thambawita
 
Intelligent agent
byGeeta Jaswani
 
Constraint satisfaction problems (csp)
byArchana432045
 
I.BEST FIRST SEARCH IN AI
byvikas dhakane
 
Informed search
byAmit Kumar Rathi
 
intelligent agent (1).pptx
byShivareddyGangam
 
Learning in AI
byMinakshi Atre
 
asymptotic notation
bySangeethaSasi1
 
Implementation of lexical analyser
byArchana Gopinath
 
Adversarial search
byNilu Desai
 
Searching
byProf.Dharmishtha R. Chaudhari
 
Bayseian decision theory
bysia16
 
Reinforcement learning
byDing Li
 
AI Lecture 2 (intelligent agents)
byTajim Md. Niamat Ullah Akhund
 
Ch 7 Knowledge Representation.pdf
byKrishnaMadala1
 
Adversarial Search
byMegha Sharma
 
Hill climbing algorithm
byDr. C.V. Suresh Babu
 
Informed search algorithms.pptx
byDr.Shweta
 

Similar to Artificial intelligence(03)

PPTX
CS Artificial intelligence chapter 2.pptx
byethiouniverse
 
PPT
Agents_AI.ppt
bysandeep54552
 
PDF
lec02_intelligentAgentsintelligentAgentsintelligentAgentsintelligentAgents
byAlvasCSE
 
PDF
Artificial intelligence what is agent and all about agent
byc8h5fzfpf6
 
PDF
Intelligent (Knowledge Based) agent in Artificial Intelligence
byKuppusamy P
 
PPTX
AI_Lec1.pptx ist step to enter in AI field
byinambscs4508
 
PPTX
Lecture 2 Agents.pptx
byAndrewKuziwakwasheMu
 
PPTX
Lecture 4 (1).pptx
bySumairaRasool6
 
PPT
Artificial intelligence and machine learning
byRiniBhandari
 
PPT
901470_Ch2.ppt901470_Ch2.ppt901470_Ch2.ppt901470_Ch2.ppt
bynashitahalwaz95
 
PPT
901470_Ch Intelligent agent introduction2.ppt
byratnababum
 
PPTX
2 Intelligent Agent articial intellligence.pptx
bygadisaAdamu
 
PPT
Artificial Intelligent Agents
byDr. Mazhar Ali Dootio
 
PPTX
Introduction to Artificial Intelligence Agents and Enviornment
byAvaniSharma51
 
PDF
AI week 2.pdf
byNayyabMirTahir
 
PPTX
Chapter 2 intelligent agents
byLukasJohnny
 
PPTX
artificial intelligence best presentation.pptx
byosmytech57
 
PPTX
Lecture 3-Artificial Intelligence.pptx Mzuzu
bycosumkondowe
 
PPTX
Intelligent Agents for Artificial intelligence.pptx
byanjanaelectronicspvt
 
PPT
Intelligent agent artificial intelligent CSE 315
byEftysInnovation
 
CS Artificial intelligence chapter 2.pptx
byethiouniverse
 
Agents_AI.ppt
bysandeep54552
 
lec02_intelligentAgentsintelligentAgentsintelligentAgentsintelligentAgents
byAlvasCSE
 
Artificial intelligence what is agent and all about agent
byc8h5fzfpf6
 
Intelligent (Knowledge Based) agent in Artificial Intelligence
byKuppusamy P
 
AI_Lec1.pptx ist step to enter in AI field
byinambscs4508
 
Lecture 2 Agents.pptx
byAndrewKuziwakwasheMu
 
Lecture 4 (1).pptx
bySumairaRasool6
 
Artificial intelligence and machine learning
byRiniBhandari
 
901470_Ch2.ppt901470_Ch2.ppt901470_Ch2.ppt901470_Ch2.ppt
bynashitahalwaz95
 
901470_Ch Intelligent agent introduction2.ppt
byratnababum
 
2 Intelligent Agent articial intellligence.pptx
bygadisaAdamu
 
Artificial Intelligent Agents
byDr. Mazhar Ali Dootio
 
Introduction to Artificial Intelligence Agents and Enviornment
byAvaniSharma51
 
AI week 2.pdf
byNayyabMirTahir
 
Chapter 2 intelligent agents
byLukasJohnny
 
artificial intelligence best presentation.pptx
byosmytech57
 
Lecture 3-Artificial Intelligence.pptx Mzuzu
bycosumkondowe
 
Intelligent Agents for Artificial intelligence.pptx
byanjanaelectronicspvt
 
Intelligent agent artificial intelligent CSE 315
byEftysInnovation
 

More from Nazir Ahmed

PPT
Data structures final lecture 1
byNazir Ahmed
 
PPT
Data structures lecture 04
byNazir Ahmed
 
PPTX
Data structure
byNazir Ahmed
 
PPT
Cover letter
byNazir Ahmed
 
PPTX
Control unit design(1)
byNazir Ahmed
 
DOCX
Computer architecture mcq (2)
byNazir Ahmed
 
PPT
Complete binary tree and heap
byNazir Ahmed
 
PPTX
Clamper clipper(10)
byNazir Ahmed
 
PPTX
Cisc mc68000
byNazir Ahmed
 
PPTX
Chapter 08
byNazir Ahmed
 
PPT
Chapter 07 ddl_sql
byNazir Ahmed
 
PPTX
Chapter 4
byNazir Ahmed
 
PPT
Chapter 03
byNazir Ahmed
 
PPTX
Chapter # 12 er modeling
byNazir Ahmed
 
PPT
Chapeter 2
byNazir Ahmed
 
PPT
Ch7 1 v1
byNazir Ahmed
 
PPT
Ch07 deadlocks
byNazir Ahmed
 
PPT
Ch05 cpu-scheduling
byNazir Ahmed
 
PPT
Ch04 threads
byNazir Ahmed
 
PPT
Ch03 processes
byNazir Ahmed
 
Data structures final lecture 1
byNazir Ahmed
 
Data structures lecture 04
byNazir Ahmed
 
Data structure
byNazir Ahmed
 
Cover letter
byNazir Ahmed
 
Control unit design(1)
byNazir Ahmed
 
Computer architecture mcq (2)
byNazir Ahmed
 
Complete binary tree and heap
byNazir Ahmed
 
Clamper clipper(10)
byNazir Ahmed
 
Cisc mc68000
byNazir Ahmed
 
Chapter 08
byNazir Ahmed
 
Chapter 07 ddl_sql
byNazir Ahmed
 
Chapter 4
byNazir Ahmed
 
Chapter 03
byNazir Ahmed
 
Chapter # 12 er modeling
byNazir Ahmed
 
Chapeter 2
byNazir Ahmed
 
Ch7 1 v1
byNazir Ahmed
 
Ch07 deadlocks
byNazir Ahmed
 
Ch05 cpu-scheduling
byNazir Ahmed
 
Ch04 threads
byNazir Ahmed
 
Ch03 processes
byNazir Ahmed
 

Recently uploaded

PDF
ASRB NET 2025 Paper GENETICS AND PLANT BREEDING ARS, SMS & STODiscussion | Co...
bySatyam Sharma
 
PPTX
Time Series Analysis - Method of Simple Moving Average 3 Year and 4 Year Movi...
bySundar B N
 
PPTX
G-Protein-Coupled Receptors (GPCRs): Structure, Mechanism, and Functions
byAnoja Kurian
 
PDF
Digital Journalism Ethics 2025 materi for Regulation & Ethic Media
byAdePutraTunggali
 
PPTX
A Presentation of PMES 2025-2028 with Salient features.pptx
byRoyPintor2
 
PPTX
Chapter 3. Pharmaceutical Aids (pharmaceutics)
bySharibJamal
 
PPTX
Physical education notes class ncert 12th
byjatinrg2009
 
PPTX
Time Series Analysis - Weighted (Unequal) Moving Average Method
bySundar B N
 
PPTX
Time Series Analysis - Meaning, Definition, Components and Application
bySundar B N
 
PDF
“Step-by-Step Fabrication of Bipolar Junction Transistors (BJTs)”
byGS Virdi
 
PDF
Digital Electronics – Registers and Their Applications
byGS Virdi
 
PDF
āĻŦāĻžāĻ‚āĻ˛āĻžāĻĻā§‡āĻļ āĻ…āĻ°ā§āĻĨāĻ¨ā§ˆāĻ¤āĻŋāĻ• āĻ¸āĻŽā§€āĻ•ā§āĻˇāĻž - ā§¨ā§Ļā§¨ā§Ģ with Bookmark.pdf
bytanbircox UJS App
 
PDF
Risk Management and Regulatory Compliance - by Ms. Oceana Wong
byagenticroom
 
PPTX
Masterclass on Cybercrime, Scams & Safety Hacks.pptx
bykalkidirwhytap
 
PDF
AI Chatbots and Prompt Engineering - by Ms. Oceana Wong
byagenticroom
 
PDF
LH_Lecture Note on Spices , AI And Importance in Human Life.pdf
bybisensharad
 
PPTX
Plant Breeding: Its History and Contribution
bySatyam Sharma
 
PPTX
General Wellness & Restorative Tonic: Draksharishta
byDr. Paindla Jyothirmai
 
PPTX
Declaration of Helsinki Basic principles in medical research ppt.pptx
byRanikonde
 
PDF
Agentic AI and AI Agents 20251121.pdf - by Ms. Oceana Wong
byagenticroom
 
ASRB NET 2025 Paper GENETICS AND PLANT BREEDING ARS, SMS & STODiscussion | Co...
bySatyam Sharma
 
Time Series Analysis - Method of Simple Moving Average 3 Year and 4 Year Movi...
bySundar B N
 
G-Protein-Coupled Receptors (GPCRs): Structure, Mechanism, and Functions
byAnoja Kurian
 
Digital Journalism Ethics 2025 materi for Regulation & Ethic Media
byAdePutraTunggali
 
A Presentation of PMES 2025-2028 with Salient features.pptx
byRoyPintor2
 
Chapter 3. Pharmaceutical Aids (pharmaceutics)
bySharibJamal
 
Physical education notes class ncert 12th
byjatinrg2009
 
Time Series Analysis - Weighted (Unequal) Moving Average Method
bySundar B N
 
Time Series Analysis - Meaning, Definition, Components and Application
bySundar B N
 
“Step-by-Step Fabrication of Bipolar Junction Transistors (BJTs)”
byGS Virdi
 
Digital Electronics – Registers and Their Applications
byGS Virdi
 
āĻŦāĻžāĻ‚āĻ˛āĻžāĻĻā§‡āĻļ āĻ…āĻ°ā§āĻĨāĻ¨ā§ˆāĻ¤āĻŋāĻ• āĻ¸āĻŽā§€āĻ•ā§āĻˇāĻž - ā§¨ā§Ļā§¨ā§Ģ with Bookmark.pdf
bytanbircox UJS App
 
Risk Management and Regulatory Compliance - by Ms. Oceana Wong
byagenticroom
 
Masterclass on Cybercrime, Scams & Safety Hacks.pptx
bykalkidirwhytap
 
AI Chatbots and Prompt Engineering - by Ms. Oceana Wong
byagenticroom
 
LH_Lecture Note on Spices , AI And Importance in Human Life.pdf
bybisensharad
 
Plant Breeding: Its History and Contribution
bySatyam Sharma
 
General Wellness & Restorative Tonic: Draksharishta
byDr. Paindla Jyothirmai
 
Declaration of Helsinki Basic principles in medical research ppt.pptx
byRanikonde
 
Agentic AI and AI Agents 20251121.pdf - by Ms. Oceana Wong
byagenticroom
 
In this document
Powered by AI

Overview of Artificial Intelligence as a field.

Definition of an intelligent agent in AI and its theoretical implications.

Agents are autonomous, flexible, and social entities acting in environments, defined by different scholars.

Agents perceive, act, and reason within environments, balancing internal and external factors.

Software agents assist users by acting on their behalf, and categorized into three groups.

Mapping functions from percepts to actions, examples include human and robotic agents.

Framework for describing agent environments through Performance measure, Environment, Actuators, and Sensors.

An agent's goals depend on its internal and external states, determining its identity in the environment.

Agents categorized into four types: simple reflex, reflex with state, goal-based, and utility-based agents.

Mechanics of simple reflex agents using condition-action rules for decision-making.

Internal state maintenance enhances decision-making in partially observable environments.

Goal-based agents adjust their actions based on goals, making them flexible.

Utility functions support agents in making quality decisions, optimizing performance.

Interaction between agents and environments is defined by their perceptual and action capabilities.

Various properties of environments including observability, determinism, and multiagent scenarios.

Classification of environments through examples, framing observable, deterministic, and other factors.

Artificial intelligence(03)

  • 1.
  • 2.
    What is anIntelligent agent? â€ĸ “Agent” can be considered as a theoretical concept from AI. â€ĸ Many different definitions exist in the literatureâ€Ļ..
  • 3.
    Agent Definition (1) â€ĸAn agent is an entity which is: – Situated in some environment. – Autonomous, in the sense that it can act without direct intervention from humans or other software processes, and controls over its own actions and internal state. – Flexible which means: â€ĸ Responsive (reactive): agents should perceive their environment and respond to changes that occur in it; â€ĸ Proactive: agents should not simply act in response to their environment, they should be able to exhibit opportunistic, goal-directed behavior and take the initiative when appropriate; â€ĸ Social: agents should be able to interact with humans or other artificial agents
  • 4.
    Agent Definition (2) AmericanHeritage Dictionary: agent- ” â€Ļ one that acts or has the power or authority to actâ€Ļ or represent another”
  • 5.
    â€ĸ "An agentis anything that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors." Russell & Norvig Agent Definition (3)
  • 6.
    “Intelligent agents continuouslyperform three functions: â€ĸ perception of dynamic conditions in the environment; â€ĸ action to affect conditions in the environment; and â€ĸ reasoning to interpret perceptions, solve problems, draw inferences, and determine actions.” Barbara Hayes-Roth Agent Definition (5)
  • 7.
    Agents & Environments īąThe agent takes sensory input from its environment, and produces as output actions that affect it. Environment sensor input action outputAgent
  • 8.
    Internal and ExternalEnvironment of an Agent Internal Environment: architecture, goals, abilities, sensors, effectors, profile, knowledge, beliefs, etc. External Environment: user, other humans, other agents, applications, information sources, their relationships, platforms, servers, networks, etc. Balance
  • 9.
    Overall Intelligent Agent [Terziyan,1993] 1) is goal-oriented, because it should have at least one goal - to keep continuously balance between its internal and external environments ; 2) is creative because of the ability to change external environment; 3) is adaptive because of the ability to change internal environment; 4) is mobile because of the ability to move to another place; 5) is social because of the ability to communicate to create a community; 6) is self-configurable because of the ability to protect “mental health” by sensing only a “suitable” part of the environment.
  • 10.
    Agent Definition Wikipedia: (Thefree Encyclopedia), īąIn computer science, an intelligent agent (IA) is a software agent that exhibits some form of artificial intelligence that assists the user and will act on their behalf, in performing non-repetitive computer- related tasks. īąWhile the working of software agents used for operator assistance or data mining is often based on fixed pre-programmed rules, "intelligent" here implies the ability to adapt and learn.
  • 11.
    Three groups ofagents [Etzioni and Daniel S. Weld, 1995] â€ĸ Backseat driver: helps the user during some task (e.g., Microsoft Office Assistant); â€ĸ Taxi driver: knows where to go when you tell the destination; â€ĸ Caretaker : know where to go, when and why.
  • 12.
    Agent’s function maps â€ĸThe agent function maps from percept histories to actions:
  • 13.
    Agents example â€ĸ Humanagent: – eyes, ears, and other organs for sensors; – hands, legs, mouth, and other body parts for actuators â€ĸ Robotic agent: – cameras and infrared range finders for sensors – various motors for actuators
  • 14.
    PEAS â€ĸ Use PEASto describe task environment – Performance measure – Environment – Actuators – Sensors â€ĸ Example: Taxi driver – Performance measure: safe, fast, comfortable (maximize profits) – Environment: roads, other traffic, pedestrians, customers – Actuators: steering, accelerator, brake, signal, horn – Sensors: cameras, sonar, speedometer, GPS, odometer, accelerometer, engine sensors
  • 15.
    PEAS â€ĸ Agent: Part-pickingrobot â€ĸ Performance measure: Percentage of parts in correct bins â€ĸ Environment: Conveyor belt with parts, bins â€ĸ Actuators: Jointed arm and hand â€ĸ Sensors: Camera, joint angle sensors
  • 16.
    PEAS â€ĸ Agent: Medicaldiagnosis system â€ĸ Performance measure: Healthy patient, minimize costs, lawsuits â€ĸ Environment: Patient, hospital, staff â€ĸ Actuators: Screen display (questions, tests, diagnoses, treatments, referrals) â€ĸ â€ĸ Sensors: Keyboard (entry of symptoms, findings, patient's answers)
  • 17.
    PEAS â€ĸ Agent: InteractiveEnglish tutor â€ĸ Performance measure: Maximize student's score on test â€ĸ Environment: Set of students â€ĸ Actuators: Screen display (exercises, suggestions, corrections) â€ĸ Sensors: Keyboard
  • 18.
    Description of Agent‘scharacter īą An agent is responsible for satisfying specific goals. There can be different types of goals such as achieving a specific status, maximising a given function (e.g., utility), etc. īą The state of an agent includes state of its internal environment + state of knowledge and beliefs about its external environment. knowledge beliefs Goal1 Goal2
  • 19.
    Connections â€ĸ An agentis situated in an environment, that consists of the objects and other agents it is possible to interact with. â€ĸ An agent has an identity that distinguishes it from the other agents of its environment. environment
  • 20.
    Agent types â€ĸ Fourbasic types in order of increasing generalization: – Simple reflex agents – Reflex agents with state/model – Goal-based agents – Utility-based agents
  • 21.
    Simple Reflex Agent ī‚ĸInstead of specifying individual mappings in an explicit table, common input-output associations are recorded ī‚— Requires processing of percepts to achieve some abstraction ī‚— Frequent method of specification is through condition-action rules ī‚ĸ if percept then action ī‚ĸ If car-in-front-is-braking then initiate-braking ī‚— Similar to innate reflexes or learned responses in humans ī‚— Efficient implementation, but limited power ī‚ĸ Environment must be fully observable ī‚ĸ Easily runs into infinite loops
  • 22.
  • 23.
    Simple Reflex Agent â€ĸfunction SIMPLE-REFLEX-AGENT (percept) returns action – static: rules, a set of condition-action rules – state ← INTERPRET-INPUT (percept) – rule ← RULE-MATCH (state, rules) – action ← RULE-ACTION [rule] – return action
  • 24.
    A simple reflexagent.. â€ĸ which works by finding a rule whose condition matches the current situation and then doing the action associated with that rule
  • 25.
    Reflex agents withstate/model â€ĸ Evan a little bit of un observability can cause serious trouble. – The braking rule given earlier assumes that the condition car-in-front-is-braking can be determined from the current percept – the current video image. â€ĸ More advanced techniques would require the maintenance of some kind of internal state to choose an action.
  • 26.
    Reflex agents withstate/model ī‚ĸ An internal state maintains important information from previous percepts ī‚— Sensors only provide a partial picture of the environment ī‚— Helps with some partially observable environments ī‚ĸ The internal states reflects the agent’s knowledge about the world ī‚— This knowledge is called a model ī‚— May contain information about changes in the world
  • 27.
    Model-based reflex agents â€ĸRequired information: – How the world evolves independently of the agent? â€ĸ An overtaking car generally will be closer behind than it was a moment ago. â€ĸ The current percept is combined with the old internal state to generate the updated description of the current state.
  • 28.
  • 29.
    Model-based reflex agents â€ĸfunction REFLEX-AGENT-WITH-STATE (percept) returns an action – static: state, a description of the current world state rules, a set of condition-action rules action, the most recent action, initially none – state ← UPDATE-STATE (state, action, percept) – rule ← RULE-MATCH (state, rules) – action ← RULE-ACTION [rule] – state ← UPDATE-STATE (state, action) – return action
  • 30.
    Goal-based agent â€ĸ Merelyknowing about the current state of the environment is not always enough to decide what to do next. â€ĸ The right decision depends on where the taxi is trying to get to. â€ĸ So the goal information is also needed.
  • 31.
    Goal-based agent â€ĸ Goal-basedagents are far more flexible. – If it starts to rain, the agent adjusts itself to the changed circumstances, since it also looks at the way its actions would affect its goals (remember doing the right thing). – For the reflex agent we would have to rewrite a large number of condition-action rules.
  • 32.
  • 33.
    Utility-based agents â€ĸ Goalsare not really enough to generate high- quality behavior. â€ĸ There are many ways to reach the destination, but some are qualitatively better than others. – More safe – Shorter – Less expensive
  • 34.
    Utility-based agent â€ĸ Wesay that if one world state is preferred to another, then it has higher utility for the agent. â€ĸ Utility is a function that maps a state onto a real number. – state → R â€ĸ Any rational agent possesses a utility function.
  • 35.
  • 36.
    Environments â€ĸ Actions aredone by the agent on the environment. â€ĸ Environment provides percepts to the agent. â€ĸ Determine to a large degree the interaction between the “outside world” and the agent – the “outside world” is not necessarily the “real world” as we perceive it â€ĸ it may be a real or virtual environment the agent lives in â€ĸ In many cases, environments are implemented within computers – They may or may not have a close correspondence to the “real world”
  • 37.
    Properties of environments â€ĸFully observable vs. partially observable â€ĸ Or Accessible vs. inaccessible – If an agent’s sensory equipment gives it access to the complete state of the environment, then we say that environment is fully observable to the agent. – An environment is effectively fully observable if the sensors detect all aspects that are relevant to the choice of action. – A fully observable environment is convenient because the agent need not maintain any internal state to keep track of the world.
  • 38.
    Properties of environments â€ĸDeterministic vs. nondeterministic. – If the next state of the environment is completely determined by the current state and the actions selected by the agents, then we say the environment is deterministic. – If the environment is inaccessible, then it may appear to be nondeterministic (bunch of uncertainties).
  • 39.
    Properties of taskenvironments â€ĸ Episodic vs. sequential. – Agent’s experience is divided into “episodes.” â€ĸ Each episode consists of the agent perceiving and acting. – Subsequent episodes do not depend on what actions occur in previous episodes. – In sequential environments current actions affect all succeeding actions
  • 40.
    Properties of taskenvironments â€ĸ Static vs. Dynamic – If the environment can change while an agent is performing action, then we say the environment is dynamic. – Else its static. – Static environments are easy to deal with, because the agent does not keep on looking at the environment while it is deciding on an action. – Semidynamic: if the environment does not change with the passage of time but the agent performance score does.
  • 41.
    Properties of environments â€ĸDiscrete vs. continuous – If there are a limited number of distinct, clearly defined percepts and actions, we say that the environment is discrete. â€ĸ Chess, since there are a fixed number of possible moves on each turn. â€ĸ Taxi driving is continuous.
  • 42.
    Properties of environments â€ĸSingle agent vs. Multiagent – In the single agent environment there is only one agent â€ĸ A computer software playing crossword puzzle – In multiagent systems, there are more than one active agents â€ĸ Video games
  • 43.
    Environment Obser vable Determi nistic Episodic Stati c DiscreteAgents Chess with a clock Chess without a clock Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent EnvironmentExamples
  • 44.
    EnvironmentExamples Environment Obser vable Determi nistic Episodic StaticDiscrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
  • 45.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker
  • 46.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi
  • 47.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon
  • 48.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi
  • 49.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi
  • 50.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis
  • 51.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single
  • 52.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis
  • 53.
    Environment Examples Environment Obser vable Determi nistic EpisodicStatic Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Fully observable vs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent
  • 54.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking
  • 55.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking Fully Determi nistic Episodic Semi Discrete Single
  • 56.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Stati c Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking Fully Determi nistic Episodic Semi Discrete Single Interactive English tutor
  • 57.
    Environment Examples Fully observablevs. partially observable Deterministic vs. stochastic / strategic Episodic vs. sequential Static vs. dynamic Discrete vs. continuous Single agent vs. multiagent Environment Obser vable Determi nistic Episodic Static Discrete Agents Chess with a clock Fully Strategic Sequential Semi Discrete Multi Chess without a clock Fully Strategic Sequential Static Discrete Multi Poker Partial Strategic Sequential Static Discrete Multi Backgammon Fully Stochast ic Sequential Static Discrete Multi Taxi driving Partial Stochast ic Sequential Dyna mic Continu ous Multi Medical diagnosis Partial Stochast ic Episodic Static Continu ous Single Image analysis Fully Determi nistic Episodic Semi Discrete Single Robot part picking Fully Determi nistic Episodic Semi Discrete Single Interactive English tutor Partial Stochast ic Sequential Dyna mic Discrete Multi