PAC-Bayesian Policy Evaluation for Reinforcement Learning

Details PAC-Bayesian Policy Evaluation for Reinforcement Learning PAC-Bayesian Policy Evaluation for Reinforcement Learning

2012-02-14

arxiv.org/abs/1202.3717v1

Computer Science

Learning

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

PAC-Bayesian Policy Evaluation for Reinforcement Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with PAC-Bayesian Policy Evaluation for Reinforcement Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and PAC-Bayesian Policy Evaluation for Reinforcement Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-90416