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
![Deep Q-LearningでFXしてみた](https://cdn-ak-scissors.b.st-hatena.com/image/square/7b26994f0060057665e9269a9cb6aacbfce40e6e/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2F161010rikkyov2forslideshare-170529064737-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)