提出可长期记忆的智能体探索框架，提升复杂环境下的持续学习能力
Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration
- 用多模态大模型+强化学习实现主动记忆查询与探索
- 在长时程任务中显著优于现有方法，提升探索效率与决策质量
- 适合研究具身智能、长期学习与多任务认知的学者
理想的具身智能体应具备终身学习能力，以应对长周期、复杂任务，实现在通用环境中的持续运行。这不仅要求完成指定任务，还需利用长期情景记忆优化决策。然而，现有主流的一次性具身任务主要关注任务完成结果，忽视了探索过程与记忆利用的重要性。为此，我们提出长期记忆具身探索（LMEE）框架，统一智能体的探索认知与决策行为，推动终身学习。同时构建了相应数据集与基准测试平台LMEE-Bench，包含多目标导航与基于记忆的问答任务，全面评估具身探索的过程与结果。为增强记忆召回与主动探索能力，提出MemoryExplorer方法，通过强化学习微调多模态大语言模型，鼓励主动记忆查询。采用包含动作预测、前沿选择与问答任务的多任务奖励函数，使模型实现主动探索。大量实验表明，该方法在长时程具身任务中显著优于现有先进模型。数据集与代码将公开于https://wangsen99.github.io/papers/lmee/
原文摘要 · Abstract (English)
An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but also to leverage long-term episodic memory to optimize decision-making. However, existing mainstream one-shot embodied tasks primarily focus on task completion results, neglecting the crucial process of exploration and memory utilization. To address this, we propose Long-term Memory Embodied Exploration (LMEE), which aims to unify the agent's exploratory cognition and decision-making behaviors to promote lifelong learning. We further construct a corresponding dataset and benchmark, LMEE-Bench, incorporating multi-goal navigation and memory-based question answering to comprehensively evaluate both the process and outcome of embodied exploration. To enhance the agent's memory recall and proactive exploration capabilities, we propose MemoryExplorer, a novel method that fine-tunes a multimodal large language model through reinforcement learning to encourage active memory querying. By incorporating a multi-task reward function that includes action prediction, frontier selection, and question answering, our model achieves proactive exploration. Extensive experiments against state-of-the-art embodied exploration models demonstrate that our approach achieves significant advantages in long-horizon embodied tasks. Our dataset and code will be released at https://wangsen99.github.io/papers/lmee/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。