オフラインメタ強化学習のための文脈潜在世界モデル
Contextual Latent World Models for Offline Meta Reinforcement Learning
オフラインのメタ強化学習において、タスク表現を潜在世界モデルに条件付けして共同学習することで、タスク依存のダイナミクスを捉える表現を獲得し、未見タスクへの汎化性能を向上させた。
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: Mohammadreza Nakheai, Aidan Scannell, Kevin Luck, Joni Pajarinen
分類: cs.LG
原文アブストラクト
Offline meta-reinforcement learning seeks to learn policies that generalize across related tasks from fixed datasets. Context-based methods infer a task representation from transition histories, but learning effective task representations without supervision remains a challenge. In parallel, latent world models have demonstrated strong self-supervised representation learning through temporal consistency. We introduce contextual latent world models, which condition latent world models on inferred task representations and train them jointly with the context encoder. This enforces task-conditioned temporal consistency, yielding task representations that capture task-dependent dynamics rather than merely discriminating between tasks. Our method learns more expressive task representations and significantly improves generalization to unseen tasks across MuJoCo, Contextual-DeepMind Control, and Meta-World benchmarks.
