Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
DL輪読会 Policy Information Capacity: Information-Theoretic Measure for…
タスクの複雑性
Policy Information Capacity
: Information-Theoretic Measure for
Task Complexity
in
Deep Reinforcement Learning
Hiroki Furuta
,
Tatsuya Matsushima
,
Tadashi Kozuno
,
Yutaka Matsuo
,
Sergey Levine
,
Ofir Nachum
,
Shixiang Shane Gu
University of Tokyo
University of Alberta
Google Research
Submitted on 23 Mar 2021
https://arxiv.org/abs/2103.12726v1