arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07294cs.LGcs.AIstat.ML
收藏

用条件作用树推广离散作用空间

Generalising Discrete Action Spaces with Conditional Action Trees

Queen Mary University of London(伦敦玛丽女王大学)

Christopher Bamford, Alvaro Ovalle

摘要:

在强化学习(RL)环境中,有相对较少的惯例来构造动作空间。因此,将RL算法应用于具有多个组件的大动作空间的任务需要额外的努力来适应不同的格式。在本文中,我们引入{ \em条件动作树}有两个主要目标:(1)作为一种在RL中构造动作空间的方法,以推广到多个动作空间规范,以及(2)通过将其分解为多个子空间来形式化一个过程,以显着减少动作空间,有利于多阶段决策方法。我们展示了几个验证我们方案的概念验证实验,从基本离散动作空间的环境到RTS风格游戏中常见的大型组合动作空间。

英文摘要:

There are relatively few conventions followed in reinforcement learning (RL) environments to structure the action spaces. As a consequence the application of RL algorithms to tasks with large action spaces with multiple components require additional effort to adjust to different formats. In this paper we introduce {\em Conditional Action Trees} with two main objectives: (1) as a method of structuring action spaces in RL to generalise across several action space specifications, and (2) to formalise a process to significantly reduce the action space by decomposing it into multiple sub-spaces, favoring a multi-staged decision making approach. We show several proof-of-concept experiments validating our scheme, ranging from environments with basic discrete action spaces to those with large combinatorial action spaces commonly found in RTS-style games.

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。

↑