arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2002.03534stat.MLcs.LG
收藏

基于离散行为的策略学习算法

Discrete Action On-Policy Learning with Action-Value Critic

UT-Austin(德克萨斯大学奥斯汀分校);Columbia University(哥伦比亚大学)

Yuguang Yue, Yunhao Tang, Mingzhang Yin, Mingyuan Zhou

摘要:

离散动作空间中的强化学习(RL)在现实世界的应用中无处不在,但其复杂性随着动作空间维度呈指数增长,这使得有效应用现有的基于策略梯度的深度RL算法具有挑战性。为了有效地在多维离散动作空间中操作,我们构造了一个评价器来估计动作值函数,将其应用于相关动作,并将这些评价器估计的动作值组合起来以控制梯度估计的方差。我们遵循严格的统计分析来设计如何生成和组合这些相关的动作,以及如何通过关闭某些维度的贡献来稀疏梯度。这些努力的结果是一个新的离散行动的政策RL算法,经验优于相关的政策算法依赖于方差控制技术。我们在OpenAI Gym基准任务上展示了这些属性,并说明了离散化动作空间如何有利于探索阶段,从而由于离散策略的灵活性而促进收敛到更好的局部最优解。

英文摘要:

Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension, making it challenging to apply existing on-policy gradient based deep RL algorithms efficiently. To effectively operate in multidimensional discrete action spaces, we construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. We follow rigorous statistical analysis to design how to generate and combine these correlated actions, and how to sparsify the gradients by shutting down the contributions from certain dimensions. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques. We demonstrate these properties on OpenAI Gym benchmark tasks, and illustrate how discretizing the action space could benefit the exploration phase and hence facilitate convergence to a better local optimal solution thanks to the flexibility of discrete policy.

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。

↑