让强化学习模型通过想象实现零样本知识迁移。
MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
- 用想象机制映射目标任务与源任务的对应实体。
- 仅需少量人工标注示例即可在新任务上零样本生效。
- 适合需要快速适应新环境的智能体开发场景。
人类擅长类比推理——只需少量调整，就能将已掌握的知识迁移到相关任务。相比之下，强化学习（RL）代理在面对结构相似的新任务时，仍需大量重新训练。本文提出MAGIK框架，使RL代理无需与目标环境交互，即可将知识迁移到类似任务。该方法通过想象机制，将目标任务中的实体映射到源领域中的对应物，从而复用原有策略。在自定义的MiniGrid和MuJoCo任务上的实验表明，MAGIK仅需少量人工标注示例，即可实现有效的零样本迁移。与现有基线对比显示，其基于想象的类比映射提供了新颖且高效的迁移机制。
原文摘要 · Abstract (English)
Humans excel at analogical reasoning - applying knowledge from one task to a related one with minimal relearning. In contrast, reinforcement learning (RL) agents typically require extensive retraining even when new tasks share structural similarities with previously learned ones. In this work, we propose MAGIK, a novel framework that enables RL agents to transfer knowledge to analogous tasks without interacting with the target environment. Our approach leverages an imagination mechanism to map entities in the target task to their analogues in the source domain, allowing the agent to reuse its original policy. Experiments on custom MiniGrid and MuJoCo tasks show that MAGIK achieves effective zero-shot transfer using only a small number of human-labelled examples. We compare our approach to related baselines and highlight how it offers a novel and effective mechanism for knowledge transfer via imagination-based analogy mapping.
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。