GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning

EasyChair Preprint 6924

Abstract

Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process. DQN found this property might cause instability for training, so it proposed effective methods to handle the downside of the property. Instead of focusing on the unfavorable aspects, we find it critical for RL to ease the gap between the estimated data distribution and the ground truth data distribution while supervised learning (SL) fails to do so. From this new perspective, we extend the basic paradigm of RL called the Generalized Policy Iteration (GPI) into a more generalized version, which is called the Generalized Data Distribution Iteration (GDI). We see massive RL algorithms and techniques can be unified into the GDI paradigm, which can be considered as one of the special cases of GDI. We provide theoretical proof of why GDI is better than GPI and how it works. Several practical algorithms based on GDI have been proposed to verify its effectiveness and extensiveness. Empirical experiments prove our state-of the-art (SOTA) performance on Arcade Learning Environment (ALE), wherein our algorithm has achieved 9620.98% mean human normalized score (HNS), 1146.39% median HNS and 22 human world record breakthroughs (HWRB) using only 200M training frames. Our work aims to lead the RL research to step into the journey of conquering the human world records and seek real superhuman agents on both performance and efficiency.

Keyphrases: Generalized Data Distribution Iteration, Human World Records, The Arcade Learning Environment

@booklet{EasyChair:6924,
  author    = {Jiajun Fan and Changnan Xiao and Yue Huang},
  title     = {GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning},
  howpublished = {EasyChair Preprint 6924},
  year      = {EasyChair, 2021}}