arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.10656cs.AI
收藏

从对称性中学习：具有对称行为与语言指令的元强化学习

Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions

Technical University of Munich（慕尼黑工业大学）；Sun Yat-sen University（中山大学）；Pazhou Lab（琶洲实验室）

Xiangtong Yao, Zhenshan Bing, Genghang Zhuang, Kejia Chen, Hongkuan Zhou, Kai Huang, Alois Knoll

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种结合对称行为与语言指令的双MDP元强化学习方法，通过利用行为与指令的对称性增强任务信息，在多个操作任务中显著提升了元强化学习的泛化能力和学习效率。

摘要：

元强化学习（meta-RL）是一种很有前景的方法，能够使智能体快速学习新任务。然而，大多数元强化学习算法在多任务场景中泛化能力较差，原因是仅由奖励提供的任务信息不足。语言条件元强化学习通过将语言指令与智能体的行为进行匹配来提升泛化能力。而行为与语言指令都具有对称性，这种对称性可以加速人类对新知识的学习。因此，将对称性和语言指令结合到元强化学习中，有助于提高算法的泛化能力和学习效率。我们提出了一种双MDP元强化学习方法，使智能体能够借助对称行为和语言指令高效地学习新任务。我们在多个具有挑战性的操作任务中评估了该方法，实验结果表明，我们的方法能够显著提升元强化学习的泛化能力和学习效率。视频见 https://tumi6robot.wixsite.com/symmetry/。

英文摘要：

Meta-reinforcement learning (meta-RL) is a promising approach that enables the agent to learn new tasks quickly. However, most meta-RL algorithms show poor generalization in multi-task scenarios due to the insufficient task information provided only by rewards. Language-conditioned meta-RL improves the generalization capability by matching language instructions with the agent's behaviors. While both behaviors and language instructions have symmetry, which can speed up human learning of new knowledge. Thus, combining symmetry and language instructions into meta-RL can help improve the algorithm's generalization and learning efficiency. We propose a dual-MDP meta-reinforcement learning method that enables learning new tasks efficiently with symmetrical behaviors and language instructions. We evaluate our method in multiple challenging manipulation tasks, and experimental results show that our method can greatly improve the generalization and learning efficiency of meta-reinforcement learning. Videos are available at https://tumi6robot.wixsite.com/symmetry/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑