image

Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings

Publication Date:

Abstract

Search is an important tool for computing effective policies in single- and multi-agent environments, and has been crucial for achieving superhuman performance in several benchmark fully and partially observable games. However, one major limitation of prior search approaches for partially observable environments is that the computational cost scales poorly with the amount of hidden information... (read more)

Authors

https://openreview.net/pdf?id=xP37gkVKa_0

0001-01-01 -