Back to Search
Start Over
Exploiting Best-Match Equations for Efficient Reinforcement Learning.
- Source :
-
Journal of Machine Learning Research . Jun2011, Vol. 12 Issue 6, p2045-2094. 50p. - Publication Year :
- 2011
-
Abstract
- This article presents and evaluates best-match learning, a new approach to reinforcement learning that trades off the sample efficiency of model-based methods with the space efficiency of model-free methods. Best-match learning works by approximating the solution to a set of best-match equations, which combine a sparse model with a model-free Q-value function constructed from samples not used by the model. We prove that, unlike regular sparse model-based methods, bestmatch learning is guaranteed to converge to the optimal Q-values in the tabular case. Empirical results demonstrate that best-match learning can substantially outperform regular sparse model-based methods, as well as several model-free methods that strive to improve the sample efficiency of temporal-difference methods. In addition, we demonstrate that best-match learning can be successfully combined with function approximation. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15324435
- Volume :
- 12
- Issue :
- 6
- Database :
- Academic Search Index
- Journal :
- Journal of Machine Learning Research
- Publication Type :
- Academic Journal
- Accession number :
- 67239944