MetaCart Sign in to MyCiteSeerX

Include Citations | Advanced Search | Help

Disambiguated Search | Include Citations | Advanced Search | Help

Multi-Agent Reinforcement Learning: a critical survey (2003) [29 citations — 0 self]

by Yoav Shoham ,  Rob Powers ,  Trond Grenager
Add To MetaCart

Abstract:

We survey the recent work in AI on multi-agent reinforcement learning (that is, learning in stochastic games). We then argue that, while exciting, this work is flawed. The fundamental flaw is unclarity about the problem or problems being addressed. After tracing a representative sample of the recent literature, we identify four well-defined problems in multi-agent reinforcement learning, single out the problem that in our view is most suitable for AI, and make some remarks about how we believe progress is to be made on this problem.

Citations

1487 Dynamic programming – Bellman - 1957
340 Markov games as a framework for multi-agent reinforcement learning – Littman - 1994
205 Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm – Hu, Wellman - 1998
197 The dynamics of reinforcement learning in cooperative multiagent systems – Claus, Boutilier - 1998
140 Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria – Erev, Roth - 1998
132 Rational learning leads to Nash equilibrium – Kalai, Lehrer - 1993
127 Learning to coordinate without sharing information – Sen, Sekaran, et al. - 1994
112 Modeling Bounded Rationality – Rubinstein - 1998
77 2001, ‘Friend-or-Foe Q-Learning in General-Sum Games – Littman
75 Formulation of Bayesian Analysis for Games with Incomplete Information – Mertens, Zamir - 1985
65 Iterative Solution of Games by Fictitious Play – Brown - 1951
57 Online learning about other agents in a dynamic multiagent system – Hu, Wellman - 1998
51 Learning mixed equilibria – Fudenberg, Kreps - 1993
51 A decisiontheoretic approach to coordinating multiagent interactions – Gmytrasiewicz, Durfee, et al. - 1991
49 Rational and convergent learning in stochastic games – Bowling, Veloso - 2001
48 Bounded complexity justifies cooperation in the finitely repeated prisoner’s dilemma – Neyman - 1985
42 Approximation to bayes risk in repeated plays,” in Contributions to the Theory of – Hannan - 1957
38 On complexity as bounded rationality – Papadimitriou, Yannakakis - 1994
34 A generalized reinforcement-learning model: Convergence and applications – Littman, Szepesvári - 1996
29 Efficient learning equilibrium – Brafman, Tennenholtz - 2004
23 Implicit negotiation in repeated games – Littman, Stone - 2001
21 Correlated-q learning – Greenwald, Hall - 2003
21 A trading agent competition for the research community – Wellman, Wurman - 1999
20 Playing is believing: The role of beliefs in multiagent learning – Chang, Kaelbling - 2001
16 Convergence problems of general-sum multiagent reinforcement learning – Bowling - 2000
16 Sophisticated EWA learning and strategic teaching in repeated games – Camerer, Ho, et al. - 2002
16 Non-computable strategies and discounted repeated games – Nachbar, Zame - 1996
11 Learning to play games in extensive form by valuation – Jehiel, Samet - 2001
4 Multiagent Q-learning – Hu, Wellman - 2002
2 E#cient learning equilibrium – Tennenholtz - 2002
View or Download | Add to My Collection | Correct Errors