arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.11329cs.LGcs.AI
收藏

基于价值序贯决策的逆策略评估

Inverse Policy Evaluation for Value-based Sequential Decision-making

University of Alberta(阿尔伯塔大学)

Alan Chan, Kris de Asis, Richard S. Sutton

摘要:

用于强化学习的基于值的方法缺乏从价值函数导出行为的普遍适用的方法。许多方法涉及近似值迭代(例如,$Q$ -学习),并以任意程度的熵相对于估计进行greening,以确保状态空间被充分探索。基于显式贪婪的行为假设值反映了\textit{some}策略的值,贪婪策略将是对该策略的改进。然而,值迭代可以产生不对应于\textit{any}策略的价值函数。这在函数逼近机制中尤其重要,因为真实的价值函数不能被完美地表示。在这项工作中,我们探讨了使用\textit{inverse policy evaluation},解决一个可能的政策给定的价值函数,从价值函数派生行为的过程。我们提供的理论和实证结果表明,逆政策评估,结合近似值迭代算法,是一种可行的方法,基于价值的控制。

英文摘要:

Value-based methods for reinforcement learning lack generally applicable ways to derive behavior from a value function. Many approaches involve approximate value iteration (e.g., $Q$-learning), and acting greedily with respect to the estimates with an arbitrary degree of entropy to ensure that the state-space is sufficiently explored. Behavior based on explicit greedification assumes that the values reflect those of \textit{some} policy, over which the greedy policy will be an improvement. However, value-iteration can produce value functions that do not correspond to \textit{any} policy. This is especially relevant in the function-approximation regime, when the true value function can't be perfectly represented. In this work, we explore the use of \textit{inverse policy evaluation}, the process of solving for a likely policy given a value function, for deriving behavior from a value function. We provide theoretical and empirical results to show that inverse policy evaluation, combined with an approximate value iteration algorithm, is a feasible method for value-based control.

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。

↑