arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.06970cs.LGcs.AIstat.ML
收藏

约束状态分布偏移的非策略策略梯度算法

Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift

Facebook AI Research(脸书人工智能研究院);McGill University(麦吉尔大学)

Riashat Islam, Komal K. Teru, Deepak Sharma, Joelle Pineau

摘要:

非策略深度强化学习(RL)算法无法在不与环境进行在线交互的情况下仅从批量离线数据中学习,这是由于被称为\textit{extrapolation error}的现象。这通常是由于重放缓冲区中可用的过去数据可能与当前策略下的数据分布完全不同。我们认为,大多数离策略学习方法从根本上遭受\textit{state distribution shift}由于行为和目标政策收集的数据的状态访问分布之间的不匹配。当前样本和过去样本之间的这种数据分布偏移会显著影响大多数现代的基于脱离策略的策略优化算法的性能。本文首先系统地分析了离策略学习中的状态分布失配问题,然后提出了一种约束状态分布偏移的离线策略优化方法。为此,我们首先使用密度估计器基于状态的特征来估计状态分布,然后开发一种新的约束非策略梯度目标,其最小化状态分布偏移。我们的连续控制任务的实验结果表明,最大限度地减少这种分布不匹配,可以显着提高性能,在最流行的实用的政策外策略梯度算法。

英文摘要:

Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from the data distribution under the current policy. We argue that most off-policy learning methods fundamentally suffer from a \textit{state distribution shift} due to the mismatch between the state visitation distribution of the data collected by the behavior and target policies. This data distribution shift between current and past samples can significantly impact the performance of most modern off-policy based policy optimization algorithms. In this work, we first do a systematic analysis of state distribution mismatch in off-policy learning, and then develop a novel off-policy policy optimization method to constraint the state distribution shift. To do this, we first estimate the state distribution based on features of the state, using a density estimator and then develop a novel constrained off-policy gradient objective that minimizes the state distribution shift. Our experimental results on continuous control tasks show that minimizing this distribution mismatch can significantly improve performance in most popular practical off-policy policy gradient 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。

↑