Diverse Exploration For Fast And Safe Policy Improvement

Abstract

We study an important yet under-addressed problem of quickly and safely improving policies in online reinforcement learning domains. As its solution, we propose a novel exploration strategy - diverse exploration (DE), which learns and deploys a diverse set of safe policies to explore the environment. We provide DE theory explaining why diversity in behavior policies enables effective exploration without sacrificing exploitation. Our empirical study shows that an online policy improvement algorithm framework implementing the DE strategy can achieve both fast policy improvement and safe online performance.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keycohen2018diverse

Related papers

• Diverse Exploration Via Conjugate Policies For Policy Gradient Methods (2019)4.52
• Data-dependent Exploration For Online Reinforcement Learning From Human Feedback (2026)0.00
• DGPO: Discovering Multiple Strategies With Diversity-guided Policy Optimization (2022)2.26
• Decoupled Exploration And Exploitation Policies For Sample-efficient Reinforcement Learning (2021)0.00
• Maximum Entropy Diverse Exploration: Disentangling Maximum Entropy Reinforcement Learning (2019)0.00
• Improving Policy Gradient By Exploring Under-appreciated Rewards (2016)0.00
• Effective Diversity In Population Based Reinforcement Learning (2020)0.00
• Learning To Explore With Meta-policy Gradient (2018)0.00