適応の前に:継続的世界モデルにおけるゼロショット汎化のボトルネック
Before We Adapt: The Zero-Shot Generalization Bottleneck in Continual World Models
継続的強化学習で世界モデルを再利用する際、物理的文脈が変わるとゼロショット性能が大きく劣化し、その度合いは観測表現に強く依存することを実験的に示した研究。
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: Amir Mesbah, Di Wu
分類: cs.LG
原文アブストラクト
Continual reinforcement learning (CRL) requires agents to operate under environmental changes while reusing prior knowledge whenever possible. We argue that model-based reinforcement learning provides a promising framework for this setting because learned world models (WMs) can, in principle, support change detection, knowledge reuse, adaptation, and acquisition of new knowledge. However, such benefits depend heavily on whether the learned model can generalize beyond the contexts in which it was trained. In this work, we propose to formulate this problem with a contextual Markov decision process in which context is decomposed into behavioral and physical components. This view organizes continual WM learning into reuse, adaptation, and acquisition of new knowledge. As a first step, we study direct reuse when behavioral rules remain unchanged. Using Dyna-Q and TD-MPC in controlled FourRooms tasks, we find that zero-shot reuse can degrade substantially under physical-context changes and that this behavior depends strongly on the observation representation used by the WM. Additional ablation studies and latent-space diagnostics suggest that learned representations do not automatically provide the invariances needed for reuse. These results identify representation generalization as an important bottleneck for reliable world-model reuse in CRL.