注目を学ぶ:部分観測強化学習における構造的注意機構による情報履歴の優先
Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning
Transformerベースの世界モデルにガウス分布的な注意の事前分布を導入し、部分観測下の強化学習で重要な遷移に柔軟に注目させることで性能を大幅に改善した。
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: Daniel De Dios Allegue, Jinke He, Frans A. Oliehoek
分類: cs.LG, cs.AI
原文アブストラクト
Transformers have shown strong ability to model long-term dependencies and are increasingly adopted as world models in model-based reinforcement learning (RL) under partial observability. However, unlike natural language corpora, RL trajectories are sparse and reward-driven, making standard self-attention inefficient because it distributes weight uniformly across all past tokens rather than emphasizing the few transitions critical for control. To address this, we introduce structured inductive priors into the self-attention mechanism of the dynamics head: (i) per-head memory-length priors that constrain attention to task-specific windows, and (ii) distributional priors that learn smooth Gaussian weightings over past state-action pairs. We integrate these mechanisms into UniZero, a model-based RL agent with a Transformer-based world model that supports planning under partial observability. Experiments on the Atari 100k benchmark show that most efficiency gains arise from the Gaussian prior, which smoothly allocates attention to informative transitions, while memory-length priors often truncate useful signals with overly restrictive cut-offs. In particular, Gaussian Attention achieves a 77% relative improvement in mean human-normalized scores over UniZero. These findings suggest that in partially observable RL domains with non-stationary temporal dependencies, discrete memory windows are difficult to learn reliably, whereas smooth distributional priors flexibly adapt across horizons and yield more robust data efficiency. Overall, our results demonstrate that encoding structured temporal priors directly into self-attention improves the prioritization of informative histories for dynamics modeling under partial observability.
関連論文
- 世界モデルは政策ランキングの正確性に必ずしも正しさを要さない:相対的限界と監査の限界強化学習/世界モデル
- DiffDreamer: 世界モデルと微分可能シミュレーションを結合した俊敏なクアッドロータ制御強化学習/世界モデル
- CyberWorld: 自律型サイバー防御のためのサンプル効率の高い世界モデル強化学習/世界モデル
- 効率的な一次強化学習のための局所・大域世界モデルの結合強化学習/世界モデル
- 因果関係を考慮した強化学習のためのオブジェクト中心の世界モデル強化学習/世界モデル
- DreamerV3-XP:不確実性推定による探索の最適化強化学習/世界モデル
