arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.03400cs.AI
收藏

相信你所看到的:离线多智能体强化学习的隐式约束方法

Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning

Tsinghua University(清华大学);Harbin Institute of Technology(哈尔滨工业大学)

Yiqin Yang, Xiaoteng Ma, Chenghao Li, Zewu Zheng, Qiyuan Zhang, Gao Huang, Jun Yang, Qianchuan Zhao

摘要:

在不与环境交互的情况下从数据集进行学习(离线学习)是将强化学习(RL)算法应用于现实世界场景的重要步骤。然而,与单智能体相比,离线多智能体强化学习引入了更多的智能体,具有更大的状态和动作空间,这是更具挑战性的,但很少受到关注。我们证明了当前离线RL算法是无效的多智能体系统,由于累积的外推误差。在本文中,我们提出了一种新的离线RL算法,名为隐式约束Q学习(ICQ),它有效地消除了外推误差,只信任的状态动作对在数据集中的值估计。此外,我们扩展了ICQ的多智能体任务的联合政策下的隐式约束的分解。实验结果表明,外推误差被成功地控制在一个合理的范围内,对代理的数量不敏感。我们进一步表明,ICQ在具有挑战性的多智能体离线任务(星际争霸II)中实现了最先进的性能。我们的代码在https://github.com/YiqinYang/ICQ上公开。

英文摘要:

Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counterpart, offline multi-agent RL introduces more agents with the larger state and action space, which is more challenging but attracts little attention. We demonstrate current offline RL algorithms are ineffective in multi-agent systems due to the accumulated extrapolation error. In this paper, we propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), which effectively alleviates the extrapolation error by only trusting the state-action pairs given in the dataset for value estimation. Moreover, we extend ICQ to multi-agent tasks by decomposing the joint-policy under the implicit constraint. Experimental results demonstrate that the extrapolation error is successfully controlled within a reasonable range and insensitive to the number of agents. We further show that ICQ achieves the state-of-the-art performance in the challenging multi-agent offline tasks (StarCraft II). Our code is public online at https://github.com/YiqinYang/ICQ.

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。

↑