A neurally plausible model learns successor representations in partially observable environments

First published at 10:25 UTC on November 7th, 2019.

Successor representations are a mid-point between model-based and model-free reinforcement learning. This paper learns successor representation in environments where only incomplete information is available.

Abstract:
Animals need to devise strate...

MORE
CategoryScience & Technology
SensitivityNormal - Content that is suitable for ages 16 and over