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, Beta Distribution, Self-Adaptive Exploration-Exploitation Trade-off, Success Rate

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 technique in reinforcement learning that addresses the sparse-reward problem by providing more frequent and informative rewards. We introduce a self-adaptive and highly efficient reward shaping mechanism that incorporates success rates derived from historical experiences as shaped rewards. The success rates are sampled from Beta distributions, which dynamically evolve from uncertain to reliable values as data accumulates. Initially, the shaped rewards exhibit more randomness to encourage exploration, while over time, the increasing certainty enhances exploitation, naturally balancing exploration and exploitation. Our approach employs Kernel Density Estimation (KDE) combined with Random Fourier Features (RFF) to derive the Beta distributions, providing a computationally efficient, non-parametric, and learning-free solution for high-dimensional continuous state spaces. Our method is validated on various tasks with extremely sparse rewards, demonstrating notable improvements in 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