让不同机器人共享任务知识，大幅减少训练数据需求。
Knowledge Reutilization in Meta-Reinforcement Learning
- 用简化模型学任务知识，再转给不同机器人使用。
- 比顶尖方法误差降低94.75%~99.79%，数据量只需其23.8%。
- 适合跨机器人部署的强化学习应用，尤其资源受限场景。
元强化学习通过提取相关任务的共性实现快速适应，但现有端到端方法常将任务推断与具体机体控制耦合，导致非参数化任务语义模糊、样本效率低，且难以跨智能体复用。本文提出一种元知识重用框架，在动力学简化的智能体上学习任务级知识，并将其迁移到异构智能体。框架采用贝叶斯非参数先验组织潜在任务模式，高阶策略生成任务级幅度引导。为连接可复用的任务知识与不同机体，引入语义-幅度接口和轻量级时序适配器，将冻结的元知识转化为时序对齐的子目标，供机体特异性底层控制器使用。在多个运动智能体上的实验表明，本框架相比最新基线方法，最终步跟踪误差降低94.75%至99.79%，且仅需约23.8%的交互数据即可达到相当的部署性能。
原文摘要 · Abstract (English)
Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample efficiency, and limit cross-agent reuse. We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents. The framework uses a Bayesian non-parametric prior to organize latent task modes and a high-level policy to generate task-level magnitude guidance. To bridge reusable task knowledge with different embodiments, we introduce a semantic-magnitude interface and a lightweight temporal adaptor, which convert frozen meta-knowledge into temporally aligned subgoals for embodiment-specific low-level controllers. Experiments on multiple locomotion agents show that our framework reduces final-step tracking error by 94.75% -- 99.79% compared with recent state-of-the-art baselines and achieves comparable deployment performance with about 23.8% of their interaction data.
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。