Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences
Keywords: reinforcement learning, data influence estimation
TL;DR: We present Policy Iteration with Turn-over Dropout (PIToD), which efficiently estimates the influence of experiences.
Abstract: In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance.
Information about how these experiences influence the agent's performance is valuable for various purposes, such as identifying experiences that negatively influence underperforming agents.
One method for estimating the influence of experiences is the leave-one-out (LOO) method.
However, this method is usually computationally prohibitive.
In this paper, we present Policy Iteration with Turn-over Dropout (PIToD), which efficiently estimates the influence of experiences.
We evaluate how accurately PIToD estimates the influence of experiences and its efficiency compared to LOO.
We then apply PIToD to amend underperforming RL agents, i.e., we use PIToD to estimate negatively influential experiences for the RL agents and to delete the influence of these experiences.
We show that RL agents' performance is significantly improved via amendments with PIToD.
Supplementary Material: zip
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 874
Loading