エンティティ中心の階層型強化学習と因子分解サブゴール拡散
Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion
複数エンティティ環境での長期目標タスクに対し、価値ベースのGCRLエージェントと因子分解サブゴール生成拡散モデルを組み合わせた階層型オフライン強化学習手法を提案し、疎報酬の画像ベース長期タスクで成功率を大幅に向上させた。
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: Dan Haramati, Carl Qi, Tal Daniel, Amy Zhang, Aviv Tamar, George Konidaris
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multiple entities. Achieving long-horizon goals in complex environments remains a core challenge in Reinforcement Learning (RL). Domains with multiple entities are particularly difficult due to their combinatorial complexity. GCRL facilitates generalization across goals and the use of subgoal structure, but struggles with high-dimensional observations and combinatorial state-spaces, especially under sparse reward. We employ a two-level hierarchy composed of a value-based GCRL agent and a factored subgoal-generating conditional diffusion model. The RL agent and subgoal generator are trained independently and composed post hoc through selective subgoal generation based on the value function, making the approach modular and compatible with existing GCRL algorithms. We introduce new variations to benchmark tasks that highlight the challenges of multi-entity domains, and show that our method consistently boosts performance of the underlying RL agent on image-based long-horizon tasks with sparse rewards, achieving over 150% higher success rates on the hardest task in our suite and generalizing to increasing horizons and numbers of entities. Rollout videos are provided at: https://sites.google.com/view/hecrl
