Papers › Offline Reinforcement Learning with Implicit Q-Learning
Offline Reinforcement Learning with Implicit Q-Learning
Ilya Kostrikov, Ashvin Nair, Sergey Levine
Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to avoid errors due to distributional shift. This trade-off is critical, because most current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy, and therefore need to either constrain these actions to be in-distribution, or else regularize their values. We propose an offline RL method that never needs to evaluate actions outside of the dataset, but still enables the learned policy to improve substantially over the best behavior in the data through generalization. The main insight in our work is that, instead of evaluating unseen actions from the latest policy, we can approximate the policy improvement step implicitly by treating the state value function as a random variable, with randomness determined by the action (while still integrating over the dynamics to avoid excessive optimism), and then taking a state conditional upper expectile of this random variable to estimate the value of the best actions in that state. This leverages the generalization capacity of the function approximator to estimate the value of the best available action at a given state without ever directly querying a Q-function with this unseen action. Our algorithm alternates between fitting this upper expectile value function and backing it up into a Q-function. Then, we extract the policy via advantage-weighted behavioral cloning. We dub our method implicit Q-learning (IQL). IQL demonstrates the state-of-the-art performance on D4RL, a standard benchmark for offline reinforcement learning. We also demonstrate that IQL achieves strong performance fine-tuning using online interaction after offline initialization.
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):
get_harvested_code_for_paper(arxiv_id="2110.06169")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2110.06169", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2110.06169")
Code
No sample from the archive's official repositories (rail-berkeley/rlkit, ikostrikov/implicit_q_learning) is linked to this paper; the 57 samples below come from 11 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from rail-berkeley/rlkit for another paper; from ikostrikov/implicit_q_learning for 2 other papers.
rail-berkeley/rlkit: Syntology's graph links these samples to Adaptive Q-Aid for Conditional Supervised Learning in Offline Reinforcement Learning (arXiv:2402.02017; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. ikostrikov/implicit_q_learning: 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) and State Advantage Weighting for Offline RL (arXiv:2210.04251; that paper's own run record: 0 ran · 5 unverified); nothing checks that they implement this paper's method.
Syntology 58 code samples: 57 from 11 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 58: 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. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 57 samples from 11 repositories, 44 ran (36 with no instrument failure; 8 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 5 of its repositories that Syntology harvested for other papers:
- rail-berkeley/rlkit, official repository: harvested for another paper, listed under the repository
- ikostrikov/implicit_q_learning, official repository: harvested for 2 other papers, listed under the repository
- takuseno/d3rlpy, community (archive-listed): harvested for another paper, listed under the repository
- opendilab/DI-engine, community (archive-listed): harvested for 4 other papers, listed under the repository
- pytorch/rl, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 45 samples that ran has no recorded date.
17 repositories listed; official and paper-mentioned ones first.
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
58 samples harvested: 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. “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.
Licence: 23 of the 58 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 11 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 11 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
b6a1eedb944158c8 · report
fixture: returned Actor · level recorded 2026-09-22 1a4179d29d5698c1 · report
fixture: returned Critic · level recorded 2026-09-22 c23983ba22a35975 · report
fixture: returned IQL · level recorded 2026-09-22 f90b550029795ff8 · report
fixture: returned Value · level recorded 2026-09-22 73d62bef000c40fa · report
fixture: returned ImplicitQLearning · level recorded 2026-09-22 e30a96134d01076a · report
fixture: signature time_str:str/0/str · returned float · level recorded 2026-09-24 b67b22a168cce1a0 · report
fixture: signature x:ndarray/1/float, y:ndarray/1/float, error:float/0/float · returned ndarray · level recorded 2026-09-24 4a012f1a3bd772ba · report
fixture: signature bytes:bytes/0/? · returned str · level recorded 2026-09-24 census: 8 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.py ran fingerprinted MIT (permissive) ·
9c4866bb7ea6847e · report
fixture: signature p0:ndarray/2/float, p1:ndarray/2/float · returned ndarray · level recorded 2026-09-24 census: 8 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket assetto_corsa_gym/AssettoCorsaEnv/gap_torch.py ran fingerprinted MIT (permissive) ·
8262bb9a6731a45a · report
fixture: signature p0:Tensor/2/float, p1:Tensor/2/float · returned Tensor · level recorded 2026-09-24 cb170ee52e2c253f · report
fixture: signature dataset_path:PosixPath/0/?, file:PosixPath/0/?, track:str/0/str, car:str/0/str · returned list · level recorded 2026-09-24 9a868703a6f4ebc5 · report
fixture: signature x:ndarray/1/float, y:ndarray/1/float · returned ndarray · level recorded 2026-09-24 9aff92bfd00fb101 · report
fixture: signature x:ndarray/1/float, y:ndarray/1/float · returned ndarray · level recorded 2026-09-24 046abc4b4ab05935 · report
fixture: signature v:ndarray/2/float · returned ndarray · level recorded 2026-09-24 30afe5f53a0af6db · report
fixture: signature v:Tensor/2/float · returned Tensor · level recorded 2026-09-24 cfb2071ad5f20847 · report
fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-24 e10139c8cfcc9897 · report
fixture: signature f:str/0/str · returned dict · level recorded 2026-09-24 b9421a30c9ec520e · report
fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-24 5fbcfd39eca9be93 · report
fixture: signature b:Tensor/1/float, e:Tensor/1/float · returned Tensor · level recorded 2026-09-24 008fedc7a27baf05 · report
b7d05dedb09fbc7e · report
3f617b1c2021d06a · report
27ef9688ee8bc0c2 · report
fixture: returned ImplicitQLearning · level recorded 2026-09-22 ba061d6a7ffd45bf · report
99526660d7c044e6 · report
fixture: returned ImplicitQLearning · level recorded 2026-09-22 census: 4 implementations from 8 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 IQL/iql.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
b2bdeb779182394b · report
fixture: signature u:Tensor/2/float, tau:float/0/float · returned Tensor · level recorded 2026-09-22 9a453c413229c3e8 · report
fixture: returned Actor · level recorded 2026-09-22 80a6ad9eabb2130a · report
fixture: returned Critic · level recorded 2026-09-22 96a8264069e38c3a · report
fixture: returned DiagGaussianActor · level recorded 2026-09-22 43876c48b7ed9f0e · report
fixture: returned MLP · level recorded 2026-09-22 ab256778314dd6eb · report
fixture: returned Value · level recorded 2026-09-22 census: 5 implementations from 6 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 IQL.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
f55fa75eaa288304 · report
fixture: signature diff:Tensor/2/float, expectile:float/0/float · returned Tensor · level recorded 2026-09-22 ec0dfb8aa1f8f95a · report
fixture: returned IQLPolicy · level recorded 2026-09-22 7c0883f7901f1f98 · report
f49a5596a23ec01c · report
fixture: returned BasePolicy · level recorded 2026-09-22 8d9ce25604e09aac · report
fixture: returned EnsembleLinear · level recorded 2026-09-22 e8ccb12a6101441f · report
fixture: returned MLP · level recorded 2026-09-22 dbb570ccd708ff1e · report
fixture: signature obj:Tensor/2/float, device:str/0/str · returned Tensor · level recorded 2026-09-22 d65d964e0519b495 · report
fixture: signature pred:Tensor/2/float, target:Tensor/2/float, expectile:float/0/float · returned Tensor · level recorded 2026-09-22 553f6d4d94d916a1 · report
fixture: signature m:callable/0/? · returned SimpleModel · level recorded 2026-09-22 be003e2209473d34 · report
fixture: signature input_dim:int/0/int, output_dim:int/0/int, norm_layer:callable/0/?, activation:callable/0/?, dropout:float/0/float, linear_layer:callable/0/? · returned list · level recorded 2026-09-22 a2e8e5d2a2240f4c · report
8f18a6efeac4cf16 · report
6970e6937dbee5a6 · report
1ea93cbf319bab05 · report
a369d99da375c4a9 · report
bc6ec59a73ed3500 · report
fixture: returned BasePolicy · level recorded 2026-09-22 d14cce65ce43e79e · report
fixture: returned IQLPolicy · level recorded 2026-09-22 966c8f4b02ba3120 · report
fixture: returned Actor · level recorded 2026-09-22 babedc4feb0bd1bc · report
fixture: returned Critic · level recorded 2026-09-22 6310a7198b14e85d · report
fixture: returned IQL · level recorded 2026-09-22 7681050968341abc · report
fixture: returned MLP · level recorded 2026-09-22 03c7a0d62a9a41b5 · report
fixture: returned ValueCritic · level recorded 2026-09-22 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 5 of 6, arg 1: rank 2, kind float, dtype float32 IQL.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
162c85e425a085c5 · report
fixture: signature diff:Tensor/2/float, expectile:float/0/float · returned Tensor · level recorded 2026-09-22 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.
census: 4 implementations from 8 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded ·
579d77f78c03773e · report
fixture: signature u:Tensor/2/float, tau:float/0/float · returned Tensor · level recorded, date not recorded 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.
10 assemblies on this paper: 10 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
10 sibling assemblies for Implicit Q-Learning (IQL) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 7 bricks; individually on a fixture: 6 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- IQL entry · level 0 · unverified ·
09d15343fe38fa60 - Actor model · level 1 · ran ·
9a453c413229c3e8 - Critic model · level 1 · ran ·
80a6ad9eabb2130a - DiagGaussianActor model · level 1 · ran ·
96a8264069e38c3a - Value model · level 1 · ran ·
ab256778314dd6eb - expectile_loss loss · level 1 · ran · our draft was wrong ·
f55fa75eaa288304 - MLP model · level 1 · ran ·
43876c48b7ed9f0e
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 10 siblings
- IQLPolicy entry · level 1 · ran ·
d14cce65ce43e79e - BasePolicy helper · level 1 · ran ·
bc6ec59a73ed3500
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- ImplicitQLearning entry · level 1 · ran ·
27ef9688ee8bc0c2 - asymmetric_l2_loss loss · level 1 · ran · our draft was wrong ·
579d77f78c03773e - update_exponential_moving_average update_rule · level 0 · unverified ·
ba061d6a7ffd45bf
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- ImplicitQLearning entry · level 1 · ran ·
99526660d7c044e6 - asymmetric_l2_loss helper · level 1 · ran · our draft was wrong ·
b2bdeb779182394b - soft_update helper · level 0 · unverified ·
1ddf841eed24fa3a
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 12 bricks; individually on a fixture: 7 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; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- IQLPolicy entry · level 0 · unverified ·
a369d99da375c4a9 - BasePolicy helper · level 1 · ran ·
f49a5596a23ec01c - DeterministicActor helper · level 0 · unverified ·
8f18a6efeac4cf16 - GaussianActor helper · level 0 · unverified ·
1ea93cbf319bab05 - convert_to_tensor helper · level 1 · ran · our draft was wrong ·
dbb570ccd708ff1e - expectile_regression helper · level 1 · ran · our draft was wrong ·
d65d964e0519b495 - make_target helper · level 1 · ran · our draft was wrong ·
553f6d4d94d916a1 - BaseActor helper · level 0 · unverified ·
a2e8e5d2a2240f4c - EnsembleMLP helper · level 0 · unverified ·
6970e6937dbee5a6 - MLP helper · level 1 · ran ·
e8ccb12a6101441f - EnsembleLinear helper · level 1 · ran ·
8d9ce25604e09aac - miniblock helper · level 1 · ran · our draft was wrong ·
be003e2209473d34
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 6 bricks; individually on a fixture: 6 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- IQL entry · level 1 · ran ·
6310a7198b14e85d - Actor model · level 1 · ran ·
966c8f4b02ba3120 - Critic model · level 1 · ran ·
babedc4feb0bd1bc - ValueCritic model · level 1 · ran ·
03c7a0d62a9a41b5 - loss loss · level 1 · ran · our draft was wrong ·
162c85e425a085c5 - MLP helper · level 1 · ran ·
7681050968341abc
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- ImplicitQLearning entry · level 1 · ran ·
73d62bef000c40fa - asymmetric_l2_loss loss · level 1 · ran · our draft was wrong ·
82a8f299419d4d83 - soft_update update_rule · level 0 · unverified ·
12fd41e242a13169
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 5 bricks; individually on a fixture: 5 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 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 10 siblings
- IQLPolicy entry · level 1 · ran ·
ec0dfb8aa1f8f95a - BasePolicy helper · level 0 · unverified ·
7c0883f7901f1f98
harvested Assembly for Implicit Q-Learning (IQL) (graph method: Implicit Q-Learning (IQL)). 6 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) · 2 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 10 siblings
- IQL entry · level 0 · unverified ·
93fc887b580bd5ce - Actor model · level 1 · ran ·
3a5956686dfd460b - EnsembledCritic model · level 1 · ran ·
8f0d43f39f0d89d8 - ValueFunction model · level 1 · ran ·
6788c15bff8f7d36 - iql_config helper · level 0 · unverified ·
26547f61628cbc43 - EnsembledLinear helper · level 1 · ran ·
b3d4a42dc71fda39
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="2110.06169") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Introduced by this paper: IQL
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