AI.news
主页教程研究工具模型AI创业讨论新闻每日简报WIKI🚀 创业库★ 投稿
AI+医疗机器人教育金融能源健康娱乐思考

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

arxiv.org
分享

View PDF HTML (experimental)

Abstract:In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this intuition with ReMax, an objective that evaluates a policy by the expected maximum return over $M$ samples, where $M$ is a positive integer, while accounting for return uncertainty. Optimizing this objective induces stochastic exploration as an emergent property, without explicit bonus terms. For efficient policy optimization, we derive a new policy-gradient formulation for ReMax and introduce ReMax PPO (RePPO), a PPO variant that optimizes ReMax while generalizing the discrete retry count $M$ to a continuous parameter $m > 0$, enabling fine-grained control of exploration. Empirically, RePPO promotes exploration, without any explicit exploration bonuses, on the MinAtar and Craftax benchmarks.

Submission history

From: Soichiro Nishimori [view email]
[v1] Fri, 29 May 2026 03:35:13 UTC (2,321 KB)