Sciweavers

Share
CORR
2012
Springer

PAC-Bayesian Policy Evaluation for Reinforcement Learning

8 years 5 months ago
PAC-Bayesian Policy Evaluation for Reinforcement Learning
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless of the correctness of the prior distribution. This paper introduces the first PAC-Bayesian bound for the batch reinforcement learning problem with function approximation. We show how this bound can be used to perform model-selection in a transfer learning scenario. Our empirical results confirm that PAC-Bayesian policy evaluation is able to leverage prior distributions when they are informative and, unlike standard Bayesian RL approaches, ignore them when they are misleading.
Mahdi Milani Fard, Joelle Pineau, Csaba Szepesv&aa
Added 20 Apr 2012
Updated 20 Apr 2012
Type Journal
Year 2012
Where CORR
Authors Mahdi Milani Fard, Joelle Pineau, Csaba Szepesvári
Comments (0)
books