LGFeb 22, 2018

Diverse Exploration for Fast and Safe Policy Improvement

arXiv:1802.08331v116 citations
AI Analysis

This addresses the under-addressed issue of safe and efficient policy improvement in online reinforcement learning, which is incremental as it builds on existing exploration methods.

The paper tackles the problem of quickly and safely improving policies in online reinforcement learning by proposing a diverse exploration strategy that learns and deploys a diverse set of safe policies, achieving both fast policy improvement and safe online performance.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes