Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning

TL;DR

This paper introduces algorithms for discovering multiple distinct solutions within a single task in offline reinforcement learning, enabling diverse behavior learning without online interaction.

Contribution

It proposes novel algorithms specifically designed for offline RL to learn multiple solutions, addressing a gap in existing research.

Findings

Algorithms successfully learn multiple qualitatively different solutions

Proposed methods demonstrate quantitative diversity in solutions

Empirical results validate effectiveness in offline RL setting

Abstract

Recent studies on online reinforcement learning (RL) have demonstrated the advantages of learning multiple behaviors from a single task, as in the case of few-shot adaptation to a new environment. Although this approach is expected to yield similar benefits in offline RL, appropriate methods for learning multiple solutions have not been fully investigated in previous studies. In this study, we therefore addressed the problem of finding multiple solutions from a single task in offline RL. We propose algorithms that can learn multiple solutions in offline RL, and empirically investigate their performance. Our experimental results show that the proposed algorithm learns multiple qualitatively and quantitatively distinctive solutions in offline RL.