arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.02121cs.LGstat.ML
收藏

学习不应该学习的东西:使用深度强化学习消除动作

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Google research(谷歌研究);Deepmind(深度思维);The Technion - Israel Institute of Technology(以色列理工学院)

Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor

摘要:

当每个状态下有许多可用动作时,学习如何行动对于强化学习(RL)代理来说是一项具有挑战性的任务,特别是当许多动作是冗余或不相关的时候。在这种情况下,有时更容易了解哪些行动不采取。在这项工作中,我们提出了一种消除干扰的深度Q网络(AE-DQN)架构,该架构将深度RL算法与消除次优动作的动作消除网络(AEN)相结合。AEN被训练来预测无效的动作,由环境提供的外部消除信号监督。仿真结果表明,在基于文本的游戏超过一千个离散的动作香草DQN相当大的加速和增加的鲁棒性。

英文摘要:

Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination Deep Q-Network (AE-DQN) architecture that combines a Deep RL algorithm with an Action Elimination Network (AEN) that eliminates sub-optimal actions. The AEN is trained to predict invalid actions, supervised by an external elimination signal provided by the environment. Simulations demonstrate a considerable speedup and added robustness over vanilla DQN in text-based games with over a thousand discrete actions.

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。

↑