arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.13690cs.LGcs.AIcs.NEstat.ML
收藏

可扩展控制中的最大变异强化学习

Maximum Mutation Reinforcement Learning for Scalable Control

University of Toronto(多伦多大学);RBC Capital Markets(加拿大皇家银行资本市场)

Karush Suri, Xiao Qi Shi, Konstantinos N. Plataniotis, Yuri A. Lawryshyn

摘要:

强化学习(RL)的进展已经证明了大状态空间的数据效率和最优控制,但以可扩展性能为代价。另一方面,遗传方法提供了可扩展性,但描述了对进化操作的超参数敏感性。然而,这两种方法的组合最近在将RL代理扩展到高维动作空间方面取得了成功。平行于最近的发展,我们提出了基于进化的软演员批评(ESAC),一个可扩展的RL算法。通过结合演化策略和软执行者-评论者(SAC),将探索从开发中抽象出来。通过这个镜头,我们使后代之间的优势技能转移,利用软赢家选择和遗传交叉在事后,同时提高超参数的敏感性,在进化中使用新的自动突变调整(AMT)。AMT逐渐取代SAC的熵框架,允许种群在尽可能随机的情况下成功完成任务,而不使用反向传播更新。在一项由高维动作空间和稀疏奖励组成的具有挑战性的运动任务的研究中,与最大熵框架相比,ESAC表现出更好的性能和样本效率。此外,ESAC提出了有效的使用硬件资源和算法开销。ESAC的完整实现可以在karush17.github.io/esac-web/上找到。

英文摘要:

Advances in Reinforcement Learning (RL) have demonstrated data efficiency and optimal control over large state spaces at the cost of scalable performance. Genetic methods, on the other hand, provide scalability but depict hyperparameter sensitivity towards evolutionary operations. However, a combination of the two methods has recently demonstrated success in scaling RL agents to high-dimensional action spaces. Parallel to recent developments, we present the Evolution-based Soft Actor-Critic (ESAC), a scalable RL algorithm. We abstract exploration from exploitation by combining Evolution Strategies (ES) with Soft Actor-Critic (SAC). Through this lens, we enable dominant skill transfer between offsprings by making use of soft winner selections and genetic crossovers in hindsight and simultaneously improve hyperparameter sensitivity in evolutions using the novel Automatic Mutation Tuning (AMT). AMT gradually replaces the entropy framework of SAC allowing the population to succeed at the task while acting as randomly as possible, without making use of backpropagation updates. In a study of challenging locomotion tasks consisting of high-dimensional action spaces and sparse rewards, ESAC demonstrates improved performance and sample efficiency in comparison to the Maximum Entropy framework. Additionally, ESAC presents efficacious use of hardware resources and algorithm overhead. A complete implementation of ESAC can be found at karush17.github.io/esac-web/.

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。

↑