反復的な方策改善による大規模言語モデルを用いた感覚運動制御
Sensory-Motor Control with Large Language Models via Iterative Policy Refinement
LLMがエージェントの記述から制御方策を生成し、評価中の性能フィードバックと感覚運動データを用いて反復的に改善することで、連続観測を連続行動に写像する制御を実現する手法を提案した。
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: Jônata Tyska Carvalho, Stefano Nolfi
分類: cs.AI, cs.HC, cs.LG, cs.RO
原文アブストラクト
We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly map continuous observation vectors to continuous action vectors. At the outset, the LLMs generate a control strategy based on a textual description of the agent, its environment, and the intended goal. This strategy is then iteratively refined through a learning process in which the LLMs are repeatedly prompted to improve the current strategy, using performance feedback and sensory-motor data collected during its evaluation. The method is validated on classic control tasks from the Gymnasium library and the inverted pendulum task from the MuJoCo library. The approach proves effective with relatively compact models such as GPT-oss:120b and Qwen2.5:72b. In most cases, it successfully identifies optimal or near-optimal solutions by integrating symbolic knowledge derived through reasoning with sub-symbolic sensory-motor data gathered as the agent interacts with its environment.
