R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning

R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning (2001)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Ronen I. Brafman , Moshe Tennenholtz , Pack Kaelbling

Citations:

176 - 9 self

BibTeX

@MISC{Brafman01r-max-,
    author = {Ronen I. Brafman and Moshe Tennenholtz and Pack Kaelbling},
    title = {R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning},
    year = {2001}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complete, but possibly inaccurate model of its environment and acts based on the optimal policy derived from this model. The model is initialized in an optimistic fashion: all actions in all states return the maximal possible reward (hence the name). During execution, it is updated based on the agent's observations. R-max improves upon several previous algorithms: (1) It is simpler and more general than Kearns and Singh's E algorithm, covering zero-sum stochastic games. (2) It has a built-in mechanism for resolving the exploration vs...

Citations

2827	Reinforcement Learning: An Introduction - Sutton, Barto - 1998
417	Markov games as a framework for multi-agent reinforcement learning - Littman - 1994
280	Learning in embedded systems - Kaelbling - 1993
275	Prioritized sweeping: Reinforcement learning with less data and less time - Moore, Atkeson - 1993
237	Multiagent reinforcement learning: theoretical framework and an algorithm - Hu, Wellman - 1998
77	Curious Model-Building Control Systems - Schmidhuber - 1991
59	Repeated Games with Incomplete Information - Aumann, Maschler - 1995
56	Efficient reinforcement learning in factored MDPs - Kearns, Koller - 1999
35	A generalized reinforcement-learning model: Convergence and applications - Littman, L, et al. - 1996
28	Learning and Equilibrium - Levine, Fudenberg
18	A NearOptimal Polynomial Time Algorithm for Learning in Certain Classes of Stochastic Games - Brafman, Tennenholtz - 1999
6	On pseudo games’, The - Banos - 1932
4	On nonterminating stochastic games - Homan, Karp - 1966
3	Dynamic Non-Bayesian Decision-Making - Monderer, Tennenholtz - 1997