Papers › Conservative Q-Learning for Offline Reinforcement Learning

Conservative Q-Learning for Offline Reinforcement Learning

8 Jun 2020NeurIPS 2020 12arXiv:2006.04779archive 2025-07-28

Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, static datasets without further interaction. However, in practice, offline RL presents a major challenge, and standard off-policy RL methods can fail due to overestimation of values induced by the distributional shift between the dataset and the learned policy, especially when training on complex and multi-modal data distributions. In this paper, we propose conservative Q-learning (CQL), which aims to address these limitations by learning a conservative Q-function such that the expected value of a policy under this Q-function lower-bounds its true value. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees. In practice, CQL augments the standard Bellman error objective with a simple Q-value regularizer which is straightforward to implement on top of existing deep Q-learning and actor-critic implementations. On both discrete and continuous control domains, we show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return, especially when learning from complex and multi-modal data distributions.

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 (aviralkumar2907/CQL) is linked to this paper; the 34 samples below come from 7 community repositories. Syntology harvested code from aviralkumar2907/CQL for another paper.

aviralkumar2907/CQL: Syntology's graph links these samples to Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning (arXiv:2608.02332; that paper's own run record: 18 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 5 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 34 code samples harvested from 7 repositories linked to this paper: 31 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 5 honoured, 2 violated, 15 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 34 samples from 7 repositories, 31 ran (22 with no instrument failure; 9 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 8 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 31 samples that ran has no recorded date.

18 repositories listed; official and paper-mentioned ones first.

aviralkumar2907/CQL officialmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning (arXiv:2608.02332; that paper's own run record: 18 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 5 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
BY571/CQL mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
corl-team/CORL mentioned on GitHubjaxSyntology: 1 sample, 0 ran · 1 unverified report
gaetanserre/lipo mentioned on GitHubAGPL-3.0Syntology: not harvested report
haosulab/ManiSkill-Learn mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations (arXiv:2107.14483; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ikostrikov/cql-results mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 7 ran (1 instrument-failed) · 0 unverified report
mehdimashayekhi/Some-RL-Implementation mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
opendilab/DI-engine mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
runamu/compositional-conservatism mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
sail-sg/offbench mentioned on GitHubjaxSyntology: not harvested report
scottemmons/youngs-cql mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories (arXiv:2210.06518; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sparkmxy/my-offlinerl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Off-Policy Deep Reinforcement Learning without Exploration (arXiv:1812.02900; that paper's own run record: 14 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
takuseno/d3rlpy mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting the Minimalist Approach to Offline Reinforcement Learning (arXiv:2305.09836; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
yihaosun1124/OfflineRL-Kit mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MOPO: Model-based Offline Policy Optimization (arXiv:2005.13239; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), COMBO: Conservative Offline Model-Based Policy Optimization (arXiv:2102.08363; that paper's own run record: 0 ran · 2 unverified), Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble (arXiv:2110.01548; that paper's own run record: 13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
young-geng/cql mentioned on GitHubpytorchMITSyntology: 12 samples, 12 ran (7 instrument-failed) · 0 unverified report
young-geng/jaxcql mentioned on GitHubjaxMITSyntology: 7 samples, 7 ran (1 instrument-failed) · 0 unverified report
pytorch/rl jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
ray-project/ray Syntology: 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

34 samples harvested: 31 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 5 honoured, 2 violated, 15 with no contract checked; 9 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
2ran · violated contract
8ran · our draft was wrong
1ran; the contract check could not run
15ran
3unverified

Licence: 19 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. For 14 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 7 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 2 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.

BY571/CQL community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Actor in 68 papers CQL-SAC/agent.py ran fingerprinted no licence file found · pointer only · 34ba8aa41bb7fa58 · report fixture: returned Actor · level recorded 2026-09-22
CQLSAC CQL-SAC/agent.py ran no licence file found · pointer only · ea10c0c769c4b484 · report fixture: returned CQLSAC · level recorded 2026-09-22
Critic in 60 papers CQL-SAC/agent.py ran no licence file found · pointer only · 00012db4f3753643 · report fixture: returned Critic · level recorded 2026-09-22
corl-team/CORL community (archive-listed) 1 sample, 0 ran · 1 unverified
ContinuousCQL algorithms/offline/cql.py unverified Apache-2.0 (permissive) · 68d38c5b86b74f05 · report
ikostrikov/cql-results community (archive-listed) 7 samples, 7 ran (1 instrument-failed) · 0 unverified
clip_magnitude in 16 papers d4rl/rlkit/pythonplusplus.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 93d28ca67303e04b · report fixture: signature value:float/0/float, magnitude:float/0/float · returned float · level recorded 2026-09-24
create_stats_ordered_dict in 25 papers d4rl/rlkit/core/eval_util.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · fadf5f762ff04cd6 · report fixture: signature name:str/0/str, data:ndarray/1/float, stat_prefix:str/0/str, always_show_all_stats:bool/0/bool, exclude_max_min:bool/0/bool · returned OrderedDict · level recorded 2026-09-24
get_average_returns in 27 papers d4rl/rlkit/core/eval_util.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · a5d10a0b704c8db7 · report fixture: signature paths:list/1/dict · returned float64 · level recorded 2026-09-24
get_flat_params in 5 papers d4rl/rlkit/core/batch_rl_algorithm.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 9b9a51e3e3be7a6e · report fixture: signature model:callable/0/? · returned ndarray · level recorded 2026-09-24
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
d4rl/rlkit/pythonplusplus.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9910e2fc297f8665 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
is_numeric in 28 papers d4rl/rlkit/pythonplusplus.py ran · violated contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 4138766e854db009 · report fixture: signature x:int/0/int · returned bool · level recorded 2026-09-24
simple_separated_format in 28 papers d4rl/rlkit/core/tabulate.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 5cb0c55f58279f59 · report fixture: signature separator:str/0/str · returned TableFormat · level recorded 2026-09-24
mehdimashayekhi/Some-RL-Implementation community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
CQLAgent CQL/agent.py ran no licence file found · pointer only · 3c29dab689543a89 · report fixture: returned CQLAgent · level recorded 2026-09-22
DDQN CQL/agent.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 82827c5a9a2325d9 · report fixture: returned DDQN · level recorded 2026-09-22
runamu/compositional-conservatism community (archive-listed) 2 samples, 0 ran · 2 unverified
CQLPolicy offlinerlkit/policy/model_free/cql.py unverified MIT (permissive) · badd95b06c97467f · report
SACPolicy in 5 papers offlinerlkit/policy/model_free/cql.py unverified MIT (permissive) · 3487f84da3586b8f · report
young-geng/cql community (archive-listed) 12 samples, 12 ran (7 instrument-failed) · 0 unverified
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
viskit/core.py ran · honoured contract MIT (permissive) · 20922c79a0929bbf · report fixture: signature l:list/1/list · returned list · level recorded, date not recorded
batch_to_torch SimpleSAC/replay_buffer.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 32231080b4b40efc · report fixture: signature batch:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-24
create_exp_name in 7 papers viskit/logging.py ran MIT (permissive) · 3743c5d43e639ab9 · report fixture: signature exp_prefix:str/0/str, exp_id:int/0/int, seed:int/0/int · returned str · level recorded 2026-09-24
dict_to_safe_json in 7 papers viskit/logging.py ran · our draft was wrong MIT (permissive) · 41279dfcda8b39e4 · report fixture: signature d:dict/0/? · returned dict · level recorded 2026-09-25
extend_and_repeat in 10 papers SimpleSAC/model.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 1e5f5f635bdf773a · report fixture: signature tensor:Tensor/2/float, dim:int/0/int, repeat:int/0/int · returned Tensor · level recorded 2026-09-22
index_batch SimpleSAC/replay_buffer.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c8b2fc80a3fc7424 · report fixture: signature batch:dict/0/?, indices:Tensor/1/int · returned dict · level recorded 2026-09-24
load_progress in 7 papers viskit/core.py ran MIT (permissive) · 965e75a1245dd833 · report fixture: signature progress_csv_path:str/0/str · returned dict · level recorded 2026-09-24
multiple_action_q_function in 6 papers SimpleSAC/model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · d06ff25d52ad20f5 · report fixture: signature forward:callable/0/? · returned function · level recorded 2026-09-24
prefix_metrics SimpleSAC/utils.py ran MIT (permissive) · d97e89c7f1953b3a · report fixture: signature metrics:dict/0/?, prefix:str/0/str · returned dict · level recorded 2026-09-25
safe_json in 6 papers viskit/logging.py ran · violated contract MIT (permissive) · 07afff96928bd142 · report fixture: signature data:dict/0/? · returned bool · level recorded 2026-09-25
sliding_mean viskit/frontend.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 40f81b1d5f51ea76 · report fixture: signature data_array:ndarray/1/float, window:int/0/int · returned ndarray · level recorded 2026-09-22
unique in 30 papers viskit/core.py ran · our draft was wrong fingerprinted MIT (permissive) · 6c7a4a9349a395e9 · report fixture: signature l:list/1/int · returned list · level recorded 2026-09-22
young-geng/jaxcql community (archive-listed) 7 samples, 7 ran (1 instrument-failed) · 0 unverified
extend_and_repeat in 10 papers JaxCQL/jax_utils.py ran MIT (permissive) here; the stored copy is pointer only · d2f199c948f2a9ed · report fixture: signature tensor:ArrayImpl/2/float, axis:int/0/int, repeat:int/0/int · returned ArrayImpl · level recorded 2026-09-24
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
viskit/frontend.py ran MIT (permissive) · 2be75b7ac1ba23d4 · report fixture: signature xs:list/1/list · returned list · level recorded 2026-09-25
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
JaxCQL/jax_utils.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · cc35af8b18b7dc58 · report fixture: signature val:ArrayImpl/2/float, target:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
multiple_action_q_function in 6 papers JaxCQL/model.py ran MIT (permissive) · 18c566cc009ddb07 · report fixture: signature forward:callable/0/? · returned function · level recorded 2026-09-24
parition_batch_train_test JaxCQL/replay_buffer.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 3f55f8769dd45c20 · report fixture: signature batch:dict/0/?, train_ratio:float/0/float · returned tuple · level recorded 2026-09-24
update_target_network in 5 papers JaxCQL/model.py ran MIT (permissive) · f23c0c9faf00d830 · report fixture: signature main_params:dict/0/?, target_params:dict/0/?, tau:float/0/float · returned dict · level recorded 2026-09-26
value_and_multi_grad JaxCQL/jax_utils.py ran MIT (permissive) · 6f4355a6f1314166 · report fixture: signature fun:callable/0/?, n_outputs:int/0/int, argnums:int/0/int, has_aux:bool/0/bool · returned function · level recorded 2026-09-25

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.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for Conservative Q-Learning (CQL) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Conservative Q-Learning (CQL) (graph method: Conservative Q-Learning (CQL)). 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 5 siblings

  1. CQLAgent entry · level 1 · ran · 3c29dab689543a89
  2. DDQN model · level 1 · ran · 82827c5a9a2325d9

harvested Assembly for Conservative Q-Learning (CQL) (graph method: Conservative Q-Learning (CQL)). 3 bricks; individually on a fixture: 2 ran (of which 1 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) · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. CQLPolicy entry · level 0 · unverified · 91630a204b4c305a
  2. SACPolicy helper · level 1 · ran · b3d37324c880e711
  3. BasePolicy helper · level 1 · ran · bc6ec59a73ed3500

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

one of 5 siblings

  1. CQLSAC entry · level 1 · ran · ea10c0c769c4b484
  2. Actor helper · level 1 · ran · 34ba8aa41bb7fa58
  3. Critic helper · level 1 · ran · 00012db4f3753643
  4. hidden_init helper · level 1 · ran · honoured contract · 24ee38e114b38bce

harvested Assembly for Conservative Q-Learning (CQL) (graph method: Conservative Q-Learning (CQL)). 3 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) · 2 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 5 siblings

  1. ContinuousCQL entry · level 0 · unverified · 68d38c5b86b74f05
  2. Scalar helper · level 1 · ran · d7ebf290cb024d50
  3. soft_update update_rule · level 0 · unverified · 12fd41e242a13169

harvested Assembly for Conservative Q-Learning (CQL) (graph method: Conservative Q-Learning (CQL)). 3 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) · 2 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 5 siblings

  1. CQLPolicy entry · level 0 · unverified · badd95b06c97467f
  2. SACPolicy helper · level 0 · unverified · 3487f84da3586b8f
  3. BasePolicy helper · level 1 · ran · bc6ec59a73ed3500

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="2006.04779") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlDQN Replay DatasetOffline RLQ-LearningReinforcement LearningReinforcement Learning (RL)continuous-controlreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDQNDense ConnectionsQ-LearningREM

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