DODT: DreamerのActor-Criticによる軌道予測を用いたオンラインDecision Transformerの強化
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting
Dreamerが生成する予測軌道とOnline Decision Transformerを組み合わせ、相互に強化し合う並列学習フレームワークを提案し、サンプル効率と報酬を改善した。
著者: Eric Hanchen Jiang, Zhi Zhang, Dinghuai Zhang, Andrew Lizarraga, Chenheng Xu, Yasi Zhang, Siyan Zhao, Zhengjie Xu, Peiyu Yu, Yuer Tang, Deqian Kong, Ying Nian Wu
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In this paper, we introduce a novel approach that combines the Dreamer algorithm's ability to generate anticipatory trajectories with the adaptive learning strengths of the Online Decision Transformer. Our methodology enables parallel training where Dreamer-produced trajectories enhance the contextual decision-making of the transformer, creating a bidirectional enhancement loop. We empirically demonstrate the efficacy of our approach on a suite of challenging benchmarks, achieving notable improvements in sample efficiency and reward maximization over existing methods. Our results indicate that the proposed integrated framework not only accelerates learning but also showcases robustness in diverse and dynamic scenarios, marking a significant step forward in model-based reinforcement learning.
