Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation

In many reinforcement learning applications, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. In this context, we propose two bootstrapping off-policy evaluation methods which use learned MDP transition models in order to estimate lower confidence bounds on policy performance with limited data. We empirically evaluate the proposed methods in a standard policy evaluation tasks. 1

Authors

• Josiah Hanna
• Peter Stone The University of Texas at Austin Sony AI
• Scott Niekum University of Massachusetts Amherst

Keywords

No keywords are indexed for this paper.