Benchmarking Batch Deep Reinforcement Learning Algorithms

Code

• github.com/MLforHealth/rl_representations
  pytorch★ 57
• github.com/thxsxth/POMDP_RLSepsis
  pytorch★ 26
• github.com/maziarg/PrivAttack-BCQ
  pytorch★ 0
• github.com/sfujim/BCQ
  pytorch★ 0
• github.com/SwarajPawar/Discrete-BCQ
  pytorch★ 0

Abstract

Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several papers showing reasonable performances under a variety of environments and batch settings. In this paper, we benchmark the performance of recent off-policy and batch reinforcement learning algorithms under unified settings on the Atari domain, with data generated by a single partially-trained behavioral policy. We find that under these conditions, many of these algorithms underperform DQN trained online with the same amount of data, as well as the partially-trained behavioral policy. To introduce a strong baseline, we adapt the Batch-Constrained Q-learning algorithm to a discrete-action setting, and show it outperforms all existing algorithms at this task.

Tasks

Reproductions