Can I read Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout on EtoBox?

Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout by Hiraoka, Takuya; Onishi, Takashi; Tsuruoka, Yoshimasa is a scholarly article available to read on EtoBox.

What is Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout about?

In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance. Information about the influence is valuable for various purposes, including experience cleansing and analysis. One method for estimating the influence of individual experiences is agent comparison, but it is prohibitively expensive when there is a large number of experiences. In this paper, we present PI+ToD as a method for efficiently estimating the influence of experiences. PI+ToD is a policy iteration that efficiently estimates the influence of experiences by utilizing turn-over dropout. We demonstrate the efficiency of PI+ToD with experiments in MuJoCo environments.

Author

Hiraoka, Takuya; Onishi, Takashi; Tsuruoka, Yoshimasa

Published

2023

Language

EN