Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning

Published: 01 May 2025, Last Modified: 18 Jun 2025ICML 2025 posterEveryoneRevisionsBibTeXCC BY 4.0
TL;DR: We propose Hyper, a novel reinforcement learning exploration algorithm that is theoretically efficient, empirically performant and hyperparameter robust.
Abstract: The exploration \& exploitation dilemma poses significant challenges in reinforcement learning (RL). Recently, curiosity-based exploration methods achieved great success in tackling hard-exploration problems. However, they necessitate extensive hyperparameter tuning on different environments, which heavily limits the applicability and accessibility of this line of methods. In this paper, we characterize this problem via analysis of the agent behavior, concluding the fundamental difficulty of choosing a proper hyperparameter. We then identify the difficulty and the instability of the optimization when the agent learns with curiosity. We propose our method, hyperparameter robust exploration (\textbf{Hyper}), which extensively mitigates the problem by effectively regularizing the visitation of the exploration and decoupling the exploitation to ensure stable training. We theoretically justify that \textbf{Hyper} is provably efficient under function approximation setting and empirically demonstrate its appealing performance and robustness in various environments.
Lay Summary: We design and build a novel exploration algorithm that is robust and efficient.
Primary Area: Reinforcement Learning
Keywords: Reinforcement Learning, Exploration, Provably Efficient, Hyperparameter Robustness
Submission Number: 4109
Loading