A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated rules, an action sampled from the full discrete action distribution predicted by the learned policy is likely to be invali...

全面介绍

书目详细资料

Principais autores:	Shengyi Huang, Santiago Ontañón
格式:	Artigo
语言:	Inglês
出版:	LibraryPress@UF 2022-05-01
丛编:	Proceedings of the International Florida Artificial Intelligence Research Society Conference
主题:	reinforcement learning deep learning deep reinforcement learning real-time strategy games implementation details invalid action masking
在线阅读:	https://journals.flvc.org/FLAIRS/article/view/130584
标签:	添加标签 没有标签, 成为第一个标记此记录!