arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06469cs.LGcs.AI
收藏

用于深度强化学习的可泛化情景记忆

Generalizable Episodic Memory for Deep Reinforcement Learning

Tsinghua University(清华大学);Peking University(北京大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Hao Hu, Jianing Ye, Guangxiang Zhu, Zhizhou Ren, Chongjie Zhang

摘要:

基于情景记忆的方法可以通过非参数记忆快速锁定过去的成功策略,提高传统强化学习的样本效率。然而,很少的努力是投入到连续域,其中一个状态是从来没有访问过两次,和以前的情节方法无法有效地跨轨迹的经验汇总。为了解决这个问题,我们提出了可概括的情景记忆(GEM),它有效地组织状态动作值的情景记忆在一个概括的方式,并支持记忆轨迹的隐式规划。GEM利用双估计器来减少规划过程中由价值传播引起的高估偏差。实证评估表明,我们的方法显着优于现有的基于概率的方法在各种MuJoCo连续控制任务。为了进一步说明我们的方法的普遍适用性,我们评估了Atari游戏与离散动作空间,这也表明了一个显着的改进基线算法。

英文摘要:

Episodic memory-based methods can rapidly latch onto past successful strategies by a non-parametric memory and improve sample efficiency of traditional reinforcement learning. However, little effort is put into the continuous domain, where a state is never visited twice, and previous episodic methods fail to efficiently aggregate experience across trajectories. To address this problem, we propose Generalizable Episodic Memory (GEM), which effectively organizes the state-action values of episodic memory in a generalizable manner and supports implicit planning on memorized trajectories. GEM utilizes a double estimator to reduce the overestimation bias induced by value propagation in the planning process. Empirical evaluation shows that our method significantly outperforms existing trajectory-based methods on various MuJoCo continuous control tasks. To further show the general applicability, we evaluate our method on Atari games with discrete action space, which also shows a significant improvement over baseline algorithms.

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。

↑