MemCtrl: MLLMを活用した身体性エージェントの能動的メモリ制御
MemCtrl: Using MLLMs as Active Memory Controllers on Embodied Agents
MLLMに学習可能なメモリヘッドを追加し、探索中の観察や内省をオンラインで取捨選択することで、身体性タスクの達成率を平均約16%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: Vishnu Sashank Dorbala, Dinesh Manocha
分類: cs.AI, cs.RO
原文アブストラクト
Foundation models rely on in-context learning for personalized decision making. The limited size of this context window necessitates memory compression and retrieval systems like RAG. These systems however often treat memory as large offline storage spaces, which is unfavorable for embodied agents that are expected to operate under strict memory and compute constraints, online. In this work, we propose MemCtrl, a novel framework that uses Multimodal Large Language Models (MLLMs) for pruning memory online. MemCtrl augments MLLMs with a trainable memory head \mu that acts as a gate to determine which observations or reflections to retain, update, or discard during exploration. We evaluate with training two types of \mu, 1) via an offline expert, and 2) via online RL, and observe significant improvement in overall embodied task completion ability on \mu-augmented MLLMs. In particular, on augmenting two low performing MLLMs with MemCtrl on multiple subsets of the EmbodiedBench benchmark, we observe that \mu-augmented MLLMs show an improvement of around 16% on average, with over 20% on specific instruction subsets. Finally, we present a qualitative analysis on the memory fragments collected by \mu, noting the superior performance of \mu augmented MLLMs on long and complex instruction types.
