Papers › AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

16 Jun 2020arXiv:2006.09359archive 2025-07-28

Ashvin Nair, Abhishek Gupta, Murtaza Dalal, Sergey Levine

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it difficult to apply in real-world settings such as robotic control. If we can instead allow RL algorithms to effectively use previously collected data to aid the online learning process, such applications could be made substantially more practical: the prior data would provide a starting point that mitigates challenges due to exploration and sample complexity, while the online training enables the agent to perfect the desired skill. Such prior data could either constitute expert demonstrations or sub-optimal prior data that illustrates potentially useful transitions. While a number of prior methods have either used optimal demonstrations to bootstrap RL, or have used sub-optimal data to train purely offline, it remains exceptionally difficult to train a policy with offline data and actually continue to improve it further with online RL. In this paper we analyze why this problem is so challenging, and propose an algorithm that combines sample efficient dynamic programming with maximum likelihood policy updates, providing a simple and effective framework that is able to leverage large amounts of offline data and then quickly perform online fine-tuning of RL policies. We show that our method, advantage weighted actor critic (AWAC), enables rapid learning of skills with a combination of prior demonstration data and online experience. We demonstrate these benefits on simulated and real-world robotics domains, including dexterous manipulation with a real multi-fingered hand, drawer opening with a robotic arm, and rotating a valve. Our results show that incorporating prior data can reduce the time required to learn a range of robotic skills to practical time-scales.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

No sample from the archive's official repository (vitchyr/rlkit) is linked to this paper; the 12 samples below come from 4 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from vitchyr/rlkit for another paper.

vitchyr/rlkit: Syntology's graph links these samples to Mildly Conservative Q-Learning for Offline Reinforcement Learning (arXiv:2206.04745; that paper's own run record: 13 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 13 code samples: 12 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 13: 10 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 4 repositories, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vitchyr/rlkit officialmentioned in papermentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mildly Conservative Q-Learning for Offline Reinforcement Learning (arXiv:2206.04745; that paper's own run record: 13 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
corl-team/CORL mentioned on GitHubjaxSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
linhlpv/Offline-and-OfflineOnline-RL mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
typoverflow/OfflineRL-Lib mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Offline Reinforcement Learning with Implicit Q-Learning (arXiv:2110.06169; that paper's own run record: 45 ran (of which 23 constructed an object rather than computing a result; 36 with no instrument failure: 0 honoured, 0 violated, 36 with no contract checked; 9 where Syntology's instrument failed) · 13 unverified) and Extreme Q-Learning: MaxEnt RL without Entropy (arXiv:2301.02328; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
zzmtsvv/rl_task mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
HzcIrving/DLRL-PlayGround pytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified 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

13 samples harvested: 10 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
9ran
3unverified

Licence: 8 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

corl-team/CORL community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
AdvantageWeightedActorCritic algorithms/finetune/awac.py ran Apache-2.0 (permissive) · d79f983080b6e99f · report fixture: returned AdvantageWeightedActorCritic · level recorded 2026-09-22
linhlpv/Offline-and-OfflineOnline-RL community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
AdvantageWeightedActorCritic AWAC/awac.py ran no licence file found · pointer only · ad518f56352757d0 · report fixture: returned AdvantageWeightedActorCritic · level recorded 2026-09-22
soft_update in 8 papers AWAC/awac.py unverified no licence file found · pointer only · 1ddf841eed24fa3a · report
zzmtsvv/rl_task community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Actor in 68 papers awac/awac.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · eecebb628e9b243d · report fixture: returned Actor · level recorded 2026-09-22
EnsembleLinear awac/awac.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4440ae74ec82d1e3 · report fixture: returned EnsembleLinear · level recorded 2026-09-22
EnsembledCritic in 7 papers awac/awac.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2bde489d14627922 · report fixture: returned EnsembledCritic · level recorded 2026-09-22
awac_config awac/awac.py ran · metamorphic tier: deterministic no licence file found · pointer only · 10cced0b9bb6e19f · report fixture: returned awac_config · level recorded 2026-09-22
AWAC awac/awac.py unverified no licence file found · pointer only · 3cb57c71a483a705 · report
HzcIrving/DLRL-PlayGround community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
AWACActor Offline RL/AWAC/Networks.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 848704f003bcbe0a · report fixture: returned AWACActor · level recorded 2026-09-22
MLPQFunction Offline RL/AWAC/Networks.py ran · metamorphic tier: deterministic MIT (permissive) · 3817b56031f35acd · report fixture: returned MLPQFunction · level recorded 2026-09-22
MLPVFunction Offline RL/AWAC/Networks.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ba9e014f75dcd55d · report fixture: returned MLPVFunction · level recorded 2026-09-22
AWActorCritic Offline RL/AWAC/Networks.py unverified MIT (permissive) · 9d49fcc185cc1eb5 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
mlp in 108 papers repository not located ran · our draft was wrong licence of this copy not recorded · 7569e2a512ec417c · report fixture: signature sizes:list/1/int, activation:callable/0/?, output_activation:callable/0/? · returned Sequential · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for AWAC (Advantage Weighted Actor Critic) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for AWAC (Advantage Weighted Actor Critic) (graph method: AWAC (Advantage Weighted Actor Critic)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. AdvantageWeightedActorCritic entry · level 1 · ran · ad518f56352757d0
  2. soft_update update_rule · level 0 · unverified · 1ddf841eed24fa3a

harvested Assembly for AWAC (Advantage Weighted Actor Critic) (graph method: AWAC (Advantage Weighted Actor Critic)). 5 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. AWActorCritic entry · level 0 · unverified · 9d49fcc185cc1eb5
  2. AWACActor model · level 1 · ran · 848704f003bcbe0a
  3. MLPQFunction model · level 1 · ran · 3817b56031f35acd
  4. MLPVFunction model · level 1 · ran · ba9e014f75dcd55d
  5. mlp model · level 1 · ran · our draft was wrong · 7569e2a512ec417c

harvested Assembly for AWAC (Advantage Weighted Actor Critic) (graph method: AWAC (Advantage Weighted Actor Critic)). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. AWAC entry · level 0 · unverified · 3cb57c71a483a705
  2. Actor model · level 1 · ran · eecebb628e9b243d
  3. EnsembledCritic model · level 1 · ran · 2bde489d14627922
  4. awac_config helper · level 1 · ran · 10cced0b9bb6e19f
  5. EnsembleLinear helper · level 1 · ran · 4440ae74ec82d1e3

harvested Assembly for AWAC (Advantage Weighted Actor Critic) (graph method: AWAC (Advantage Weighted Actor Critic)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. AdvantageWeightedActorCritic entry · level 1 · ran · d79f983080b6e99f
  2. soft_update update_rule · level 0 · unverified · 12fd41e242a13169

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2006.09359") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Reinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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