身体性エージェントの訓練のための適応的環境生成に向けて
Towards Adaptive Environment Generation for Training Embodied Agents
エージェントの性能に基づいて難易度を適応させる閉ループ環境生成の概念実証を提案し、より効率的な学習と汎化を実現する。
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: Teresa Yeo, Dulaj Weerakoon, Dulanga Weerakoon, Archan Misra
分類: cs.RO
原文アブストラクト
Embodied agents struggle to generalize to new environments, even when those environments share similar underlying structures to their training settings. Most current approaches to generating these training environments follow an open-loop paradigm, without considering the agent's current performance. While procedural generation methods can produce diverse scenes, diversity without feedback from the agent is inefficient. The generated environments may be trivially easy, providing limited learning signal. To address this, we present a proof-of-concept for closed-loop environment generation that adapts difficulty to the agent's current capabilities. Our system employs a controllable environment representation, extracts fine-grained performance feedback beyond binary success or failure, and implements a closed-loop adaptation mechanism that translates this feedback into environment modifications. This feedback-driven approach generates training environments that more challenging in the ways the agent needs to improve, enabling more efficient learning and better generalization to novel settings.
