This document discusses self-supervised representation learning (SRL) for reinforcement learning tasks. SRL learns state representations by using prediction tasks as an auxiliary objective. The key ideas are: (1) SRL learns an encoder that maps observations to states using a prediction task like modeling future states or actions; (2) The learned state representations improve generalization and exp
![[DL輪読会]`強化学習のための状態表現学習 -より良い「世界モデル」の獲得に向けて-](https://cdn-ak-scissors.b.st-hatena.com/image/square/cacac72ff67d780fdba578daec37c426bc599f25/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2F20181026staterepresenration-181127055206-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)