The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to learn a large number of diverse behaviors, or growing-size models that scale poorly with the number of tasks. In this work, we aim to strike a better balance between an agent's size and performance by designing a method that grows adaptively depending on the task sequence. We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of tasks. The subspace's high expressivity allows CSP to perform well for many different tasks while growing sublinearly with the number of tasks. Our method does not suffer from forgetting and displays positive transfer to new tasks. CSP outperforms a number of popular baselines on a wide range of scenarios from two challenging domains, Brax (locomotion) and Continual World (manipulation).

翻译：持续获取新知识和新技能的能力对于自主智能体至关重要。现有方法通常基于固定规模模型（难以学习大量多样化行为）或增长规模模型（随任务数量增加而扩展性差）。本研究旨在通过设计一种根据任务序列自适应增长的策略，在智能体规模与性能之间取得更优平衡。我们提出持续策略子空间（CSP），这是一种新方法，通过逐步构建策略子空间来训练强化学习智能体处理连续任务序列。该子空间的高表达能力使CSP能在众多不同任务中表现优异，同时其规模增长低于任务数量的线性增长。本方法不会遭受灾难性遗忘，并能对后续任务产生正向迁移。在两个挑战性领域（Brax运动控制与持续世界操控）的广泛场景中，CSP的表现优于多个主流基线方法。