|国家预印本平台
首页|Probabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning

Probabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning

Probabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning

来源:Arxiv_logoArxiv
英文摘要

We investigate efficient exploration strategies of environments with unknown stochastic dynamics and sparse rewards. Specifically, we analyze first the impact of parallel simulations on the probability of reaching rare states within a finite time budget. Using simplified models based on random walks and L\'evy processes, we provide analytical results that demonstrate a phase transition in reaching probabilities as a function of the number of parallel simulations. We identify an optimal number of parallel simulations that balances exploration diversity and time allocation. Additionally, we analyze a restarting mechanism that exponentially enhances the probability of success by redirecting efforts toward more promising regions of the state space. Our findings contribute to a more qualitative and quantitative theory of some exploration schemes in reinforcement learning, offering insights into developing more efficient strategies for environments characterized by rare events.

Paola Bermolen、Matthieu Jonckheere、Seva Shneer、Ernesto Garcia

计算技术、计算机技术

Paola Bermolen,Matthieu Jonckheere,Seva Shneer,Ernesto Garcia.Probabilistic Insights for Efficient Exploration Strategies in Reinforcement Learning[EB/OL].(2025-03-05)[2025-05-15].https://arxiv.org/abs/2503.03565.点此复制

评论