组合任务持续学习的世界模型基准测试

中文摘要 AI 辅助

世界模型的一个理想特性是能够跨任务持续学习，适应新环境而不遗忘智能体已学到的知识。特别是，保留和重用从先前经验中获得知识的能力，支撑着智能体高效适应新环境的能力，因为物理世界的动态通常可以用重复出现的机制来描述。然而，世界模型的适应度量纠缠了两种能力：学习未见任务的速度和能力，以及重用已获取知识的能力，因为新任务在带来重复内容的同时也携带了新颖内容。为了将知识重用与先前经验分离，我们提出了一个用于机器人操作中世界模型的组合持续学习基准。具体来说，我们设计了每个任务课程，包含组合任务，这些任务结合了序列中已见任务的各个方面。我们进一步沿动作和感知两个轴分解这种组合，以更好地理解不同输入模态如何成为知识重用的瓶颈。我们在典型的持续学习方法下评估了最先进的世界模型，同时评估了一个模块化世界模型，其动态骨干包含显式可重用的组件。结果表明，模块化在平衡重用与遗忘方面优于传统方法，但没有任何方法完全解决该问题，为构建旨在重用而不遗忘的持续世界模型留下了明确的空间。更多细节可在我们的项目网站上获取：此 https URL。

英文摘要

A desirable property of a world model is the ability to learn continually across tasks, adapting to new environments without forgetting what the agent has already learnt. In particular, the ability to retain and reuse knowledge obtained from prior experiences underpins an agent's ability to efficiently adapt to novel environments, as the dynamics of the physical world can often be described in recurring mechanisms. However, the world model's measure of adaptation entangles two abilities: the speed and capacity to learn unseen tasks, and the reuse of knowledge already acquired, since incoming tasks carry novel content alongside what recurs. In order to isolate knowledge reuse from prior experiences, we propose a compositional continual learning benchmark for world models in robot manipulation. Specifically, we design each task curriculum with compositional tasks that combine aspects of the tasks seen in the sequence. We further factorise this composition along the axes of action and perception to better understand how different input modalities bottleneck knowledge reuse. We evaluate state-of-the-art world models under canonical continual learning methods, alongside a modular world model whose dynamics backbone contains explicitly reusable components. Results show that modularity balances reuse against forgetting better than conventional methods, but none solve the problem fully, leaving clear room for continual world models built to reuse without forgetting. More details are available on our project website: https://object814.github.io/Compositional-Continual-Learning/.

发表机构

• University of Oxford（牛津大学）

机构由 AI 辅助整理，请以论文原文为准。