Papers › Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

24 Oct 2019arXiv:1910.10897archive 2025-07-28

Tianhe Yu, Deirdre Quillen, Zhanpeng He, Ryan Julian, Avnish Narayan, Hayden Shively, Adithya Bellathur, Karol Hausman, Chelsea Finn, Sergey Levine

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 7 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.

PaperPDFCodeCode Syntology ran

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

The archive's official repository (rlworkgroup/metaworld) was not harvested; the 9 samples below come from 2 community repositories.

Syntology 9 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 2 repositories, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed). 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rlworkgroup/metaworld officialmentioned in papermentioned on GitHubMITSyntology: not harvested report
CAVED123/METAWORLD mentioned on GitHubMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
EdNiehues/simulacao-de-projeto-para-mapeamento mentioned on GitHubMITSyntology: not harvested report
RamnathKumar181/Adversarial-Learning-Dynamics-in-RL mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
avivne/bilinear-transduction mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Extrapolate: A Transductive Approach (arXiv:2304.14329; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
farama-foundation/metaworld mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Meta-World+: An Improved, Standardized, RL Benchmark (arXiv:2505.11289; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
mazpie/mime mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
uoe-agents/sami mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning (arXiv:2406.04815; that paper's own run record: 7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yiwc/robotics-world mentioned on GitHubMITSyntology: 7 samples, 5 ran (3 instrument-failed) · 2 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

9 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
4ran
2unverified

Licence: 6 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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. “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 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

CAVED123/METAWORLD community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
normalize_image in 28 papers metaworld/core/image_env.py ran MIT (permissive) · f725932e0f8878f4 · report fixture: returned ndarray · level recorded 2026-09-25
unormalize_image metaworld/core/image_env.py ran fingerprinted MIT (permissive) · 57b9f4dd9833bb0b · report fixture: signature image:ndarray/3/float · returned ndarray · level recorded 2026-09-25
yiwc/robotics-world community (archive-listed) 7 samples, 5 ran (3 instrument-failed) · 2 unverified
assert_fully_parsed metaworld/policies/policy.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 582e0882ba1584f1 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-26
full_v1_path_for metaworld/envs/asset_path_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e13df24e0d039aa9 · report fixture: returned str · level recorded 2026-09-26
full_v2_path_for metaworld/envs/asset_path_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 061fee9f0adfe735 · report fixture: returned str · level recorded 2026-09-26
move in 8 papers metaworld/policies/policy.py ran fingerprinted MIT (permissive) · 12487fb8bcdf3af8 · report fixture: signature from_xyz:ndarray/1/float, to_xyz:ndarray/1/float, p:float/0/float · returned ndarray · level recorded 2026-09-24
rect_prism_tolerance metaworld/envs/reward_utils.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 2062fd5a0d31ec29 · report fixture: signature curr:ndarray/1/float, zero:ndarray/1/float, one:ndarray/1/float · returned float64 · level recorded 2026-09-26
inverse_tolerance metaworld/envs/reward_utils.py unverified MIT (permissive) here; the stored copy is pointer only · 8d198fb67929603e · report
tolerance metaworld/envs/reward_utils.py unverified MIT (permissive) here; the stored copy is pointer only · ee2247985031162b · report

Tasks

Meta Reinforcement LearningMeta-LearningMulti-Task LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Datasets

Introduced by this paper, per the archive.

Meta-World Benchmark

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Meta-Learning ML10 MAML Meta-test success rate 36% #1 of 6 Archive leaderboard report
Meta-Learning ML10 MAML Meta-train success rate 25% #1 of 6 Archive leaderboard report
Meta-Learning ML10 RL^2 Meta-test success rate 10% #2 of 6 Archive leaderboard report
Meta-Learning ML10 RL^2 Meta-train success rate 50% #2 of 6 Archive leaderboard report
Meta-Learning ML10 PEARL Meta-test success rate 0% #4 of 6 Archive leaderboard report
Meta-Learning ML10 PEARL Meta-train success rate 42.78% #4 of 6 Archive leaderboard report
Meta-Learning MT50 Multi-task multi-head SAC Average Success Rate 35.85% #2 of 4 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