タスクトークン:行動基盤モデルを柔軟に適応させる手法
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
強化学習でタスク特化のエンコーダを学習し、凍結した行動基盤モデルへの追加入力トークンとして使うことで、汎用性を保ちながら特定タスクに適応させる手法を提案。
著者: Ron Vainshtein, Zohar Rimon, Shie Mannor, Chen Tessler
分類: cs.LG, cs.RO
原文アブストラクト
Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs often require meticulous prompt engineering for specific tasks, potentially yielding suboptimal results. We introduce "Task Tokens", a method to effectively tailor BFMs to specific tasks while preserving their flexibility. Our approach leverages the transformer architecture of BFMs to learn a new task-specific encoder through reinforcement learning, keeping the original BFM frozen. This allows incorporation of user-defined priors, balancing reward design and prompt engineering. By training a task encoder to map observations to tokens, used as additional BFM inputs, we guide performance improvement while maintaining the model's diverse control characteristics. We demonstrate Task Tokens' efficacy across various tasks, including out-of-distribution scenarios, and show their compatibility with other prompting modalities. Our results suggest that Task Tokens offer a promising approach for adapting BFMs to specific control tasks while retaining their generalization capabilities.
