Expertness based cooperative Q-learning

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Volumn 32, Issue 1, 2002, Pages 66-76

  Ahmadabadi, Majid Nili ^a,b   Asadpour, Masoud ^b  

^a UNIVERSITY OF TEHRAN   (Iran)

^b INSTITUTE FOR STUDIES IN THEORETICAL PHYSICS AND MATHEMATICS IPM   (Iran)

Author keywords

Cooperative learning; Expertness; Multi agent systems; Q learning

Indexed keywords

INTELLIGENT AGENTS; KNOWLEDGE ENGINEERING; LEARNING ALGORITHMS; MULTI AGENT SYSTEMS; SPURIOUS SIGNAL NOISE;

COOPERATIVE LEARNING METHOD; HUNTER-PREY SYSTEMS; Q-LEARNING; WEIGHTED STRATEGY SHARING;

LEARNING SYSTEMS;

EID: 0036465258     PISSN: 10834419     EISSN: None     Source Type: Journal    
DOI: 10.1109/3477.979961     Document Type: Article

References (35)

1. A comparison of methods for learning and combining evidence from multiple model
2. Techniques for combining multiple learners
3. Robot see, robot do: An overview of robot imitation
4. Learning, cooperation, and coordination in multi-agent systems
5. The dynamics of reinforcement learning in cooperative multiagent systems
6. Ant colony system: A cooperative learning approach to the traveling salesman problem
7. Learning and communication in multi-agent systems
8. Multi-agent learning through collective memory
9. A multi-strategy learning scheme for agent knowledge acquisition
10. A robot controller using learning by imitation
11. Committees of decision trees
12. Multi-agent reinforcement learning: Theoretical framework and an algorithm
13. Learning procedures from interactive natural language instructions
14. Experimental comparison of a heterogenous learning multi-agent system with a homogenous one
15. The development of shared experience learning in a group of mobile robots
16. Learning by watching: Extracting reusable task knowledge from visual observation of human performance
17. A cooperative ensemble learning system
18. Creating advice-taking reinforcement learners
19. Incorporating advice into agents that learn from reinforcements
20. Simulating co-evolution with mimetism
21. Transforming declarative advice into effective procedures: A heuristic search example
22. Expertness measuring in cooperative learning
23. Toward instructable connectionist systems
24. Scaling up: Distributed machine learning with cooperation
25. Improving generalization of constructive neural networks using ensembles
26. Some studies in machine learning using the game of checkers
27. On combining artificial neural nets
28. Learning to predict by the methods of temporal differences
29. Multi-agent reinforcement learning: Independent vs. cooperative agents
30. Learning from delayed rewards
31. Q-learning (technical note)
32. Speed up reinforcement learning between two agents with adaptive mimetism
33. Multi-agent reinforcement learning adaptive mimetism
34. Learning cooperative behaviors with spontaneous mimetism