Least-Squares Policy Iteration

Least-Squares Policy Iteration (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Michail G. Lagoudakis , Ronald Parr , L. Bartlett

Venue:	Journal of Machine Learning Research
Citations:	281 - 8 self

BibTeX

@ARTICLE{Lagoudakis03least-squarespolicy,
    author = {Michail G. Lagoudakis and Ronald Parr and L. Bartlett},
    title = {Least-Squares Policy Iteration},
    journal = {Journal of Machine Learning Research},
    year = {2003},
    volume = {4},
    pages = {2003}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We propose a new approach to reinforcement learning for control problems which combines value-function approximation with linear architectures and approximate policy iteration.

Citations

3523	Reinforcement Learning: An Introduction - Sutton, Barto
1249	Learning from delayed rewards - Watkins - 1989
484	Dynamic Programming and Markov Processes - Howard - 1960
458	Neuronlike adaptive elements that can solve difficult learning control problems - Barto, Sutton, et al. - 1983
342	Generalization in reinforcement learning: Successful examples using sparse coarse coding - Sutton - 1996
310	Policy gradient methods for reinforcement learning with function approximation - Sutton, McAllester, et al. - 2000
235	Temporal credit assignment in reinforcement learning - Sutton - 1984
203	Pegasus: A policy search method for large mdps and pomdps - Ng, Jordan - 2000
185	Reinforcement Learning for Robots Using Neural Networks - Lin - 1993
168	Tsitsiklis, “Actor-critic algorithms - Konda, John, et al. - 2001
167	Linear Least-Squares algorithms for temporal difference learning - Bradtke, Barto - 1996
162	Policy invariance under reward transformations: Theory and application to reward shaping - Ng, Harada, et al. - 1999
92	Kernel-based reinforcement learning - Ormoneit, Sen - 2002
88	Generalized polynomial approximation in Markovian decision processes - Schweitzer, Seidman - 1985
81	Technical update: Least-squares temporal difference learning - Boyan - 2002
71	An approach to fuzzy control of nonlinear systems: Stability and design issues - Wang, Tanaka, et al. - 1996
70	Policy iteration for factored MDPs - Koller, Parr - 2000
63	Least Squares Policy Evaluation Algorithms with Linear Function Approximation,” Discrete Event Dynamic Systems - Nedić, Bertsekas - 2003
56	Learning to drive a bicycle using reinforcement learning and shaping - Randløv, Alstrom - 1998
55	Reinforcement learning applied to linear quadratic regulation - Bradtke - 1993
47	Error Bounds for Approximate Policy Iteration - Munos
35	Policy search via density estimation - Ng, Parr, et al. - 2000
25	Infinite-horizon gradient-based policy search - Baxter, Bartlett - 2001
9	A simulation study of alternatives to ordinary least squares (with discussion - AP, Schatzoff, et al. - 1977
9	Learning to drive a bicycle using reinforcement learning and shaping - Randlv, Alstrm - 1998