Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning

Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima, Tze-Yun Leong

Keywords: Reinforcement Learning, Reward Shaping, Thompson Sampling, Self-Adaptive Exploration-Exploitation Balance

TL;DR: We propose a self-adaptive and highly efficient reward shaping mechanism by incorporating historical success rates into shaped rewards to improve sample efficiency and convergence stability in sparse-reward reinforcement learning environments.

Abstract: Reward shaping is a reinforcement learning technique that addresses the sparse-reward problem by providing frequent, informative feedback. We propose an efficient self-adaptive reward-shaping mechanism that uses success rates derived from historical experiences as shaped rewards. The success rates are sampled from Beta distributions, which evolve from uncertainty to reliability as data accumulates. Initially, shaped rewards are stochastic to encourage exploration, gradually becoming more certain to promote exploitation and maintain a natural balance between exploration and exploitation. We apply Kernel Density Estimation (KDE) with Random Fourier Features (RFF) to derive Beta distributions, providing a computationally efficient solution for continuous and high-dimensional state spaces. Our method, validated on tasks with extremely sparse rewards, improves sample efficiency and convergence stability over relevant baselines.

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: 7252