因果オブジェクト中心モデルによるモンテカルロ木探索計画
Causal Object-Centric Models for Planning with Monte Carlo Tree Search
オブジェクト中心表現と因果注意を組み合わせたモデルベース強化学習アルゴリズムCOMETを提案し、複数のベンチマークで初期学習性能を向上させた。
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: Rodion Vakhitov, Leonid Ugadiarov, Alexey Skrynnik, Aleksandr Panov
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use object-causal attention, modulating token interactions by learned per-slot relevance scores so that decision-making concentrates on task-relevant entities. COMET adds an explicit object-level inductive bias to MuZero-style latent planning. Across eight visually and dynamically diverse tasks from the Object-Centric Visual RL benchmark, ManiSkill, Robosuite, and VizDoom, COMET achieves a higher mean normalized score during the early stages of training compared to object-centric and monolithic baselines.
