arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.11490cs.LGcs.AIcs.NE
收藏

具有状态抽象的神经元情节控制

Neural Episodic Control with State Abstraction

Kyushu University(九州大学);Technical University of Munich(慕尼黑工业大学);NetEase Fuxi AI Lab(网易伏羲人工智能实验室);Singapore Management University(新加坡管理大学);University of Alberta(阿尔伯塔大学);The University of Tokyo(东京大学);Tianjin University(天津大学)

Zhuo Li, Derui Zhu, Yujing Hu, Xiaofei Xie, Lei Ma, Yan Zheng, Yan Song, Yingfeng Chen, Jianjun Zhao

摘要:

现有的深度强化学习(Deep Reinforcement Learning,DRL)算法存在样本效率低的问题。通常,基于情景控制的方法是利用高回报的过去经验来提高DRL算法的样本效率的解决方案。然而,先前的基于情景控制的方法未能利用来自历史行为的潜在信息(例如,状态转换、拓扑相似性等)并且在DRL训练期间缺乏可扩展性。这项工作介绍了神经情节控制与状态抽象(NECSA),一个简单但有效的基于状态抽象的情节控制包含一个更全面的情景记忆,一个新的状态评估,和一个多步骤的状态分析。我们评估了OpenAI健身房领域中MuJoCo和Atari任务的方法。实验结果表明,NECSA实现了更高的样本效率比国家的最先进的基于情节控制的方法。我们的数据和代码可在项目网站\footnote{\url{https://sites.google.com/view/drl-necsa}}上获得。

英文摘要:

Existing Deep Reinforcement Learning (DRL) algorithms suffer from sample inefficiency. Generally, episodic control-based approaches are solutions that leverage highly-rewarded past experiences to improve sample efficiency of DRL algorithms. However, previous episodic control-based approaches fail to utilize the latent information from the historical behaviors (e.g., state transitions, topological similarities, etc.) and lack scalability during DRL training. This work introduces Neural Episodic Control with State Abstraction (NECSA), a simple but effective state abstraction-based episodic control containing a more comprehensive episodic memory, a novel state evaluation, and a multi-step state analysis. We evaluate our approach to the MuJoCo and Atari tasks in OpenAI gym domains. The experimental results indicate that NECSA achieves higher sample efficiency than the state-of-the-art episodic control-based approaches. Our data and code are available at the project website\footnote{\url{https://sites.google.com/view/drl-necsa}}.

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。

↑