Robotics & Perception/Reinforcement Learning

[Advanced Topics] 02. Representation Learning for RL

이 글은 2023년 가을학기 AI707 이기민 교수님 수업을 듣고 복습차 필자의 이해를 위해 정리한 글입니다.

RL from pixel is difficult.

  1. Poor sample-efficiency
  2. Poor generalization on different environment

Representation learning resolves these issue.

  • What is representation learning; Learning the represenation of the data, which contain useful information for ML methods.
    • However, this is also true that optimizing a main task objective might not be enough to obtain a good representation.
  • Possible ways
    • Auxiliary task
    • Data augmentation