Papers › Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

1 Oct 2019arXiv:1910.00177archive 2025-07-28

Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can accommodate continuous and discrete actions, and can be implemented in just a few lines of code on top of standard supervised learning methods. We provide a theoretical motivation for AWR and analyze its properties when incorporating off-policy data from experience replay. We evaluate AWR on a suite of standard OpenAI Gym benchmark tasks, and show that it achieves competitive performance compared to a number of well-established state-of-the-art RL algorithms. AWR is also able to acquire more effective policies than most off-policy algorithms when learning from purely static datasets with no additional environmental interactions. Furthermore, we demonstrate our algorithm on challenging continuous control tasks with highly complex simulated characters.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

NitinVishalKulkarni/OfflineReinforcementLearning mentioned on GitHubSyntology: not harvested report
fomorians-oss/awr mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
google/trax mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hierarchical Transformers Are More Efficient Language Models (arXiv:2110.13711; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
nvlabs/gbrl_sb3 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
peisuke/awr mentioned on GitHubSyntology: not harvested report
xbpeng/awr tfMITSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Continuous ControlOpenAI GymReinforcement LearningReinforcement Learning (RL)continuous-controlregressionreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
OpenAI Gym Ant-v2 AWR Mean Reward 5067 #2 of 2 Archive leaderboard report
OpenAI Gym HalfCheetah-v2 AWR Mean Reward 9136 #2 of 2 Archive leaderboard report
OpenAI Gym Hopper-v2 AWR Mean Reward 3405 #2 of 2 Archive leaderboard report
OpenAI Gym Humanoid-v2 AWR Average Return 4996 #1 of 1 Archive leaderboard report
OpenAI Gym LunarLander-v2 AWR Average Return 229 #2 of 2 Archive leaderboard report
OpenAI Gym Walker2d-v2 AWR Mean Reward 5813 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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