SlideShare a Scribd company logo
1 of 11
Download to read offline
NEERAJ BEDI
FOUNDER MADHAWK GAMES
Briefly About Reinforcement
Learning which we are using in
our Esports project?
Reinforcement learning learns by
interacting with its environment.
There are some key terms that
are important in Reinforcement
Learning
Like
Reward
Reward is An immediate return
given to an agent when agent
performs specific action or
assignment
Environment
Environment is just the Physical
world where the agent is
interacting
Policy
Policy is Method to map the
agent’s state to actions
Value
Value means rewards which we
receive after the agent takes
some action
Some Important Attribute of
Reinforcement Learning 
1.
You work with reward signal it’s
either positive or negative
2.
Time plays a crucial role, and
you need to wait for Feedback
 
In robotics, Reinforcement
learning is used to enable the
robot to create an efficient
system for itself which learns
from its own experience and
behaviour 
And Reinforcement learning can
be used in different things like
Gaming, Manufacturing, Delivery
Management healthcare and
online stock trading
now let's discuss how we are
using reinforcement learning in
esports
In our esports project we are
training NPC in every session,
The non-player character or NPC
receives rewards by performing
correctly and penalties for
performing incorrectly
We can use this technique is so
many other ways like if we have
an AI car in the game which
needs to go to destination
without crashing into trees, we
will use reinforcement learning
to train the car and you don’t
need to program full route 
You just need to give positive
feedback and negative feedback
when it crashes into trees you
just need to give penalties, And
it will be an automatic process
and even if you replace with
different maps it will learn, so
this will be really efficient you
don’t need to program it again
and again
In the last When Not to Use
Reinforcement Learning?
When you have enough data to
solve the problem
You need to remember that
Reinforcement Learning needs
heavy resources,
So you need to analyse where
you can use reinforcement
learning

More Related Content

Similar to Briefly About Reinforcement Learning which we are using in our Esports project?

Aste v2 3
Aste v2 3Aste v2 3
Aste v2 3webb20
 
GAMING BOT USING REINFORCEMENT LEARNING
GAMING BOT USING REINFORCEMENT LEARNINGGAMING BOT USING REINFORCEMENT LEARNING
GAMING BOT USING REINFORCEMENT LEARNINGIRJET Journal
 
DevLearn: Blending Game Design and ID for VR Training
DevLearn: Blending Game Design and ID for VR TrainingDevLearn: Blending Game Design and ID for VR Training
DevLearn: Blending Game Design and ID for VR TrainingWilliam West
 
A Primer On Play: How to use Games for Learning and Results
A Primer On Play: How to use Games for Learning and ResultsA Primer On Play: How to use Games for Learning and Results
A Primer On Play: How to use Games for Learning and ResultsSharon Boller
 
Briefly About Imitation Learning
Briefly About Imitation LearningBriefly About Imitation Learning
Briefly About Imitation LearningNeeraj Bedi
 
Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017
Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017
Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017MLconf
 
Gamification for Growth Hackers -theflyy
Gamification for Growth Hackers -theflyyGamification for Growth Hackers -theflyy
Gamification for Growth Hackers -theflyyFlyyx Tech
 
Machine Learning in Unity - How to give your game AI a real brain
Machine Learning in Unity - How to give your game AI a real brainMachine Learning in Unity - How to give your game AI a real brain
Machine Learning in Unity - How to give your game AI a real brainDevGAMM Conference
 
Types of machine learning
Types of machine learningTypes of machine learning
Types of machine learningHimaniAloona
 
Game-based Learning Webinar by GreenBooks & Gamelearn
Game-based Learning Webinar by GreenBooks & GamelearnGame-based Learning Webinar by GreenBooks & Gamelearn
Game-based Learning Webinar by GreenBooks & GamelearnShyam Sunder
 
Rewards And Recognition : A different prespective
Rewards And Recognition : A different prespectiveRewards And Recognition : A different prespective
Rewards And Recognition : A different prespectivepateldivakar
 
Introduction to Reinforcement Learning.pdf
Introduction to Reinforcement Learning.pdfIntroduction to Reinforcement Learning.pdf
Introduction to Reinforcement Learning.pdfAbhinavNautiyal8
 
Designing Games for Industrial Training.
Designing Games for Industrial Training.Designing Games for Industrial Training.
Designing Games for Industrial Training.SeriousGamesAssoc
 
Game Based Learnning: Negotiation & Leadership skills game
Game Based Learnning: Negotiation & Leadership skills gameGame Based Learnning: Negotiation & Leadership skills game
Game Based Learnning: Negotiation & Leadership skills gameGreenBooks Learning Solutions
 

Similar to Briefly About Reinforcement Learning which we are using in our Esports project? (20)

Aste v2 3
Aste v2 3Aste v2 3
Aste v2 3
 
Organizational behaviour
Organizational behaviourOrganizational behaviour
Organizational behaviour
 
GAMING BOT USING REINFORCEMENT LEARNING
GAMING BOT USING REINFORCEMENT LEARNINGGAMING BOT USING REINFORCEMENT LEARNING
GAMING BOT USING REINFORCEMENT LEARNING
 
Train da trainer
Train da trainerTrain da trainer
Train da trainer
 
DevLearn: Blending Game Design and ID for VR Training
DevLearn: Blending Game Design and ID for VR TrainingDevLearn: Blending Game Design and ID for VR Training
DevLearn: Blending Game Design and ID for VR Training
 
A Primer On Play: How to use Games for Learning and Results
A Primer On Play: How to use Games for Learning and ResultsA Primer On Play: How to use Games for Learning and Results
A Primer On Play: How to use Games for Learning and Results
 
Briefly About Imitation Learning
Briefly About Imitation LearningBriefly About Imitation Learning
Briefly About Imitation Learning
 
Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017
Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017
Ben Lau, Quantitative Researcher, Hobbyist, at MLconf NYC 2017
 
Gamification for Growth Hackers -theflyy
Gamification for Growth Hackers -theflyyGamification for Growth Hackers -theflyy
Gamification for Growth Hackers -theflyy
 
Agile gamification
Agile gamificationAgile gamification
Agile gamification
 
Machine Learning in Unity - How to give your game AI a real brain
Machine Learning in Unity - How to give your game AI a real brainMachine Learning in Unity - How to give your game AI a real brain
Machine Learning in Unity - How to give your game AI a real brain
 
Reinforcement learning
Reinforcement learningReinforcement learning
Reinforcement learning
 
Reinforcement Learning using OpenAI Gym
Reinforcement Learning using OpenAI GymReinforcement Learning using OpenAI Gym
Reinforcement Learning using OpenAI Gym
 
Types of machine learning
Types of machine learningTypes of machine learning
Types of machine learning
 
Game-based Learning Webinar by GreenBooks & Gamelearn
Game-based Learning Webinar by GreenBooks & GamelearnGame-based Learning Webinar by GreenBooks & Gamelearn
Game-based Learning Webinar by GreenBooks & Gamelearn
 
Rewards And Recognition : A different prespective
Rewards And Recognition : A different prespectiveRewards And Recognition : A different prespective
Rewards And Recognition : A different prespective
 
Introduction to Reinforcement Learning.pdf
Introduction to Reinforcement Learning.pdfIntroduction to Reinforcement Learning.pdf
Introduction to Reinforcement Learning.pdf
 
Designing Games for Industrial Training.
Designing Games for Industrial Training.Designing Games for Industrial Training.
Designing Games for Industrial Training.
 
Game Based Learnning: Negotiation & Leadership skills game
Game Based Learnning: Negotiation & Leadership skills gameGame Based Learnning: Negotiation & Leadership skills game
Game Based Learnning: Negotiation & Leadership skills game
 
Intelligent agents part ii
Intelligent agents part iiIntelligent agents part ii
Intelligent agents part ii
 

More from Neeraj Bedi

3 Steps How Esports developers can give great user experience?
3 Steps How Esports developers can give great user experience?3 Steps How Esports developers can give great user experience?
3 Steps How Esports developers can give great user experience?Neeraj Bedi
 
Benefits of Voice Inputs in Esports!
Benefits of Voice Inputs in Esports!Benefits of Voice Inputs in Esports!
Benefits of Voice Inputs in Esports!Neeraj Bedi
 
WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...
WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...
WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...Neeraj Bedi
 
AR AND ITS FUTURE
AR AND ITS FUTUREAR AND ITS FUTURE
AR AND ITS FUTURENeeraj Bedi
 
WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?
WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?
WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?Neeraj Bedi
 
What Game Engine you should choose Unity or Unreal Engine?
What Game Engine you should choose Unity or Unreal Engine?What Game Engine you should choose Unity or Unreal Engine?
What Game Engine you should choose Unity or Unreal Engine?Neeraj Bedi
 

More from Neeraj Bedi (6)

3 Steps How Esports developers can give great user experience?
3 Steps How Esports developers can give great user experience?3 Steps How Esports developers can give great user experience?
3 Steps How Esports developers can give great user experience?
 
Benefits of Voice Inputs in Esports!
Benefits of Voice Inputs in Esports!Benefits of Voice Inputs in Esports!
Benefits of Voice Inputs in Esports!
 
WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...
WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...
WHY ESPORTS WEBSITE IS VITAL FOR THE SUC CESS OF ESPORTS AND 4 MUST-HAVE FEAT...
 
AR AND ITS FUTURE
AR AND ITS FUTUREAR AND ITS FUTURE
AR AND ITS FUTURE
 
WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?
WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?
WHY PEOPLE NEVER TALK ABOUT THIS REALITY OF ENTREPRENEURSHIP?
 
What Game Engine you should choose Unity or Unreal Engine?
What Game Engine you should choose Unity or Unreal Engine?What Game Engine you should choose Unity or Unreal Engine?
What Game Engine you should choose Unity or Unreal Engine?
 

Recently uploaded

Encryption Recap: A Refresher on Key Concepts
Encryption Recap: A Refresher on Key ConceptsEncryption Recap: A Refresher on Key Concepts
Encryption Recap: A Refresher on Key Conceptsthomashtkim
 
Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...
Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...
Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...Abortion Clinic
 
Navigation in flutter – how to add stack, tab, and drawer navigators to your ...
Navigation in flutter – how to add stack, tab, and drawer navigators to your ...Navigation in flutter – how to add stack, tab, and drawer navigators to your ...
Navigation in flutter – how to add stack, tab, and drawer navigators to your ...Flutter Agency
 
Test Automation Design Patterns_ A Comprehensive Guide.pdf
Test Automation Design Patterns_ A Comprehensive Guide.pdfTest Automation Design Patterns_ A Comprehensive Guide.pdf
Test Automation Design Patterns_ A Comprehensive Guide.pdfkalichargn70th171
 
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-CloudAlluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-CloudAlluxio, Inc.
 
GraphSummit Milan - Neo4j: The Art of the Possible with Graph
GraphSummit Milan - Neo4j: The Art of the Possible with GraphGraphSummit Milan - Neo4j: The Art of the Possible with Graph
GraphSummit Milan - Neo4j: The Art of the Possible with GraphNeo4j
 
Incident handling is a clearly defined set of procedures to manage and respon...
Incident handling is a clearly defined set of procedures to manage and respon...Incident handling is a clearly defined set of procedures to manage and respon...
Incident handling is a clearly defined set of procedures to manage and respon...Varun Mithran
 
Rapidoform for Modern Form Building and Insights
Rapidoform for Modern Form Building and InsightsRapidoform for Modern Form Building and Insights
Rapidoform for Modern Form Building and Insightsrapidoform
 
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4jGraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4jNeo4j
 
Effective Strategies for Wix's Scaling challenges - GeeCon
Effective Strategies for Wix's Scaling challenges - GeeConEffective Strategies for Wix's Scaling challenges - GeeCon
Effective Strategies for Wix's Scaling challenges - GeeConNatan Silnitsky
 
Modern binary build systems - PyCon 2024
Modern binary build systems - PyCon 2024Modern binary build systems - PyCon 2024
Modern binary build systems - PyCon 2024Henry Schreiner
 
COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...
COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...
COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...naitiksharma1124
 
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024MulesoftMunichMeetup
 
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Workshop -  Architecting Innovative Graph Applications- GraphSummit MilanWorkshop -  Architecting Innovative Graph Applications- GraphSummit Milan
Workshop - Architecting Innovative Graph Applications- GraphSummit MilanNeo4j
 
Jax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined DeckJax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined DeckMarc Lester
 
A Deep Dive into Secure Product Development Frameworks.pdf
A Deep Dive into Secure Product Development Frameworks.pdfA Deep Dive into Secure Product Development Frameworks.pdf
A Deep Dive into Secure Product Development Frameworks.pdfICS
 
Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14VMware Tanzu
 
Automate your OpenSIPS config tests - OpenSIPS Summit 2024
Automate your OpenSIPS config tests - OpenSIPS Summit 2024Automate your OpenSIPS config tests - OpenSIPS Summit 2024
Automate your OpenSIPS config tests - OpenSIPS Summit 2024Andreas Granig
 

Recently uploaded (20)

Encryption Recap: A Refresher on Key Concepts
Encryption Recap: A Refresher on Key ConceptsEncryption Recap: A Refresher on Key Concepts
Encryption Recap: A Refresher on Key Concepts
 
Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...
Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...
Abortion Pill Prices Jane Furse ](+27832195400*)[ 🏥 Women's Abortion Clinic i...
 
Navigation in flutter – how to add stack, tab, and drawer navigators to your ...
Navigation in flutter – how to add stack, tab, and drawer navigators to your ...Navigation in flutter – how to add stack, tab, and drawer navigators to your ...
Navigation in flutter – how to add stack, tab, and drawer navigators to your ...
 
Test Automation Design Patterns_ A Comprehensive Guide.pdf
Test Automation Design Patterns_ A Comprehensive Guide.pdfTest Automation Design Patterns_ A Comprehensive Guide.pdf
Test Automation Design Patterns_ A Comprehensive Guide.pdf
 
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-CloudAlluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
 
Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...
Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...
Abortion Pill Prices Germiston ](+27832195400*)[ 🏥 Women's Abortion Clinic in...
 
GraphSummit Milan - Neo4j: The Art of the Possible with Graph
GraphSummit Milan - Neo4j: The Art of the Possible with GraphGraphSummit Milan - Neo4j: The Art of the Possible with Graph
GraphSummit Milan - Neo4j: The Art of the Possible with Graph
 
Incident handling is a clearly defined set of procedures to manage and respon...
Incident handling is a clearly defined set of procedures to manage and respon...Incident handling is a clearly defined set of procedures to manage and respon...
Incident handling is a clearly defined set of procedures to manage and respon...
 
Rapidoform for Modern Form Building and Insights
Rapidoform for Modern Form Building and InsightsRapidoform for Modern Form Building and Insights
Rapidoform for Modern Form Building and Insights
 
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4jGraphSummit Milan - Visione e roadmap del prodotto Neo4j
GraphSummit Milan - Visione e roadmap del prodotto Neo4j
 
Effective Strategies for Wix's Scaling challenges - GeeCon
Effective Strategies for Wix's Scaling challenges - GeeConEffective Strategies for Wix's Scaling challenges - GeeCon
Effective Strategies for Wix's Scaling challenges - GeeCon
 
Modern binary build systems - PyCon 2024
Modern binary build systems - PyCon 2024Modern binary build systems - PyCon 2024
Modern binary build systems - PyCon 2024
 
COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...
COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...
COMPUTER AND ITS COMPONENTS PPT.by naitik sharma Class 9th A mittal internati...
 
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
Anypoint Code Builder - Munich MuleSoft Meetup - 16th May 2024
 
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
Workshop -  Architecting Innovative Graph Applications- GraphSummit MilanWorkshop -  Architecting Innovative Graph Applications- GraphSummit Milan
Workshop - Architecting Innovative Graph Applications- GraphSummit Milan
 
Abortion Pill Prices Turfloop ](+27832195400*)[ 🏥 Women's Abortion Clinic in ...
Abortion Pill Prices Turfloop ](+27832195400*)[ 🏥 Women's Abortion Clinic in ...Abortion Pill Prices Turfloop ](+27832195400*)[ 🏥 Women's Abortion Clinic in ...
Abortion Pill Prices Turfloop ](+27832195400*)[ 🏥 Women's Abortion Clinic in ...
 
Jax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined DeckJax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined Deck
 
A Deep Dive into Secure Product Development Frameworks.pdf
A Deep Dive into Secure Product Development Frameworks.pdfA Deep Dive into Secure Product Development Frameworks.pdf
A Deep Dive into Secure Product Development Frameworks.pdf
 
Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14
 
Automate your OpenSIPS config tests - OpenSIPS Summit 2024
Automate your OpenSIPS config tests - OpenSIPS Summit 2024Automate your OpenSIPS config tests - OpenSIPS Summit 2024
Automate your OpenSIPS config tests - OpenSIPS Summit 2024
 

Briefly About Reinforcement Learning which we are using in our Esports project?

  • 1. NEERAJ BEDI FOUNDER MADHAWK GAMES Briefly About Reinforcement Learning which we are using in our Esports project?
  • 2. Reinforcement learning learns by interacting with its environment. There are some key terms that are important in Reinforcement Learning
  • 3. Like Reward Reward is An immediate return given to an agent when agent performs specific action or assignment Environment Environment is just the Physical world where the agent is interacting
  • 4. Policy Policy is Method to map the agent’s state to actions Value Value means rewards which we receive after the agent takes some action
  • 5. Some Important Attribute of Reinforcement Learning  1. You work with reward signal it’s either positive or negative 2. Time plays a crucial role, and you need to wait for Feedback  
  • 6. In robotics, Reinforcement learning is used to enable the robot to create an efficient system for itself which learns from its own experience and behaviour  And Reinforcement learning can be used in different things like Gaming, Manufacturing, Delivery Management healthcare and online stock trading
  • 7. now let's discuss how we are using reinforcement learning in esports In our esports project we are training NPC in every session, The non-player character or NPC receives rewards by performing correctly and penalties for performing incorrectly
  • 8. We can use this technique is so many other ways like if we have an AI car in the game which needs to go to destination without crashing into trees, we will use reinforcement learning to train the car and you don’t need to program full route 
  • 9. You just need to give positive feedback and negative feedback when it crashes into trees you just need to give penalties, And it will be an automatic process and even if you replace with different maps it will learn, so this will be really efficient you don’t need to program it again and again
  • 10. In the last When Not to Use Reinforcement Learning?
  • 11. When you have enough data to solve the problem You need to remember that Reinforcement Learning needs heavy resources, So you need to analyse where you can use reinforcement learning