Papers › Benchmarking Batch Deep Reinforcement Learning Algorithms

Benchmarking Batch Deep Reinforcement Learning Algorithms

3 Oct 2019arXiv:1910.01708archive 2025-07-28

Scott Fujimoto, Edoardo Conti, Mohammad Ghavamzadeh, Joelle Pineau

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

MLforHealth/rl_representations mentioned on GitHubpytorch report
SwarajPawar/Discrete-BCQ mentioned on GitHubpytorch report
maziarg/PrivAttack-BCQ mentioned on GitHubpytorch report
sfujim/BCQ mentioned on GitHubpytorch report
thxsxth/POMDP_RLSepsis mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingDeep Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDQNDense ConnectionsQ-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections