OPRIDE: データセット内探索によるオフライン選好ベース強化学習
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
オフライン選好ベース強化学習において、クエリ効率を高めるための探索戦略と割引スケジューリングを組み合わせた手法を提案し、少ないクエリで高性能を達成した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yiqin Yang, Hao Hu, Yihuan Mao, Jin Zhang, Chengjie Wu, Yuhua Jiang, Xu Yang, Runpeng Xie, Yi Fan, Bo Liu, Yang Gao, Bo Xu, Chongjie Zhang
分類: cs.LG, cs.AI
原文アブストラクト
Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong barrier for PbRL. In this work, we address the problem of low query efficiency in offline PbRL, pinpointing two primary reasons: inefficient exploration and overoptimization of learned reward functions. In response to these challenges, we propose a novel algorithm, \textbf{O}ffline \textbf{P}b\textbf{R}L via \textbf{I}n-\textbf{D}ataset \textbf{E}xploration (OPRIDE), designed to enhance the query efficiency of offline PbRL. OPRIDE consists of two key features: a principled exploration strategy that maximizes the informativeness of the queries and a discount scheduling mechanism aimed at mitigating overoptimization of the learned reward functions. Through empirical evaluations, we demonstrate that OPRIDE significantly outperforms prior methods, achieving strong performance with notably fewer queries. Moreover, we provide theoretical guarantees of the algorithm's efficiency. Experimental results across various locomotion, manipulation, and navigation tasks underscore the efficacy and versatility of our approach.
