Prof. Mohammad-R.Akbarzadeh-T
Ferdowsi University of Mashhad
A Presentation by:
• Hosein Mohebbi
• M.-Sajad Abvisani
 Deep Blue vs Kasparov in 1997
 Freestyle Chess Tournament in 2005.Who won?
2
 We live in a multi-agent world
 Robustness
 Scalability
 Reusability of constituents
3
 A Goal of AI and Robotics:
Robust and fully autonomous agent in the real world
 Sense,decide and action
 Improve from experience (Machine learning)
 Interact with other agents (Multiagent system)
 MAS+ML in RoboCup
4
 Layered Learning
 Machine learning: exploit data to train
 Learning in one layer feeds into next layer
 First applied in simulated robot soccer [Stone & Veloso, 1997]
Layered Learning in Multi-Agent Systems Peter Stone
 Ad hoc teamwork
 PLASTIC-Policy Algorithm
 Samuel Barret, Peter Stone
5
 Bitcoin Mining Pools: A Cooperative Game Theoretic
Analysis[Here]
 Multi-issue automated negotiation with different strategies for a
car dealer business scenario[Here]
6
 A learning Multi-Agent system that mines the Web to advise
students[Here]
7
 Kiva Robots in amazon warehouse[Here]
 Agent based Control for Microgrids[Here]
 Influence in Classification via Cooperative Game Theory[Here]
8
GRASP
 Supervised by Prof. Vijay Kumar
 Creation building map
 Precision Agriculture
 Search and Rescue
9
 Some papers
 A Multiagent Approach to Autonomous Intersection Management[Here]
 A Platform for Evaluating Autonomous Intersection Management Policies[Here]
 Cooperative driving: an ant colony system for autonomous intersection
management[Here]
10
 Society of Mind (1986)
- Marvin Minsky
 Machine Learning for Agents and Multi-Agent Systems
- Daniel Kudenko (University ofYork, UK),Dimitar
Kazakov (University ofYork, UK) and Eduardo Alonso
(City University, UK)
 A Concise Introduction to Multiagent Systems and
Distributed Artificial Intelligence (Synthesis Lectures on
Artificial Intelligence and Machine Learning)
- Nikos Vlassis
 Intelligent Agent Software Engineering
- Valentina Plekhanova (University of Sunderland,UK)
11
Multi Agent Systems and Machine Learning

Multi Agent Systems and Machine Learning

  • 1.
    Prof. Mohammad-R.Akbarzadeh-T Ferdowsi Universityof Mashhad A Presentation by: • Hosein Mohebbi • M.-Sajad Abvisani
  • 2.
     Deep Bluevs Kasparov in 1997  Freestyle Chess Tournament in 2005.Who won? 2
  • 3.
     We livein a multi-agent world  Robustness  Scalability  Reusability of constituents 3
  • 4.
     A Goalof AI and Robotics: Robust and fully autonomous agent in the real world  Sense,decide and action  Improve from experience (Machine learning)  Interact with other agents (Multiagent system)  MAS+ML in RoboCup 4
  • 5.
     Layered Learning Machine learning: exploit data to train  Learning in one layer feeds into next layer  First applied in simulated robot soccer [Stone & Veloso, 1997] Layered Learning in Multi-Agent Systems Peter Stone  Ad hoc teamwork  PLASTIC-Policy Algorithm  Samuel Barret, Peter Stone 5
  • 6.
     Bitcoin MiningPools: A Cooperative Game Theoretic Analysis[Here]  Multi-issue automated negotiation with different strategies for a car dealer business scenario[Here] 6
  • 7.
     A learningMulti-Agent system that mines the Web to advise students[Here] 7
  • 8.
     Kiva Robotsin amazon warehouse[Here]  Agent based Control for Microgrids[Here]  Influence in Classification via Cooperative Game Theory[Here] 8
  • 9.
    GRASP  Supervised byProf. Vijay Kumar  Creation building map  Precision Agriculture  Search and Rescue 9
  • 10.
     Some papers A Multiagent Approach to Autonomous Intersection Management[Here]  A Platform for Evaluating Autonomous Intersection Management Policies[Here]  Cooperative driving: an ant colony system for autonomous intersection management[Here] 10
  • 11.
     Society ofMind (1986) - Marvin Minsky  Machine Learning for Agents and Multi-Agent Systems - Daniel Kudenko (University ofYork, UK),Dimitar Kazakov (University ofYork, UK) and Eduardo Alonso (City University, UK)  A Concise Introduction to Multiagent Systems and Distributed Artificial Intelligence (Synthesis Lectures on Artificial Intelligence and Machine Learning) - Nikos Vlassis  Intelligent Agent Software Engineering - Valentina Plekhanova (University of Sunderland,UK) 11