Papers › Mildly Conservative Q-Learning for Offline Reinforcement Learning
Mildly Conservative Q-Learning for Offline Reinforcement Learning
Jiafei Lyu, Xiaoteng Ma, Xiu Li, Zongqing Lu
Offline reinforcement learning (RL) defines the task of learning from a static logged dataset without continually interacting with the environment. The distribution shift between the learned policy and the behavior policy makes it necessary for the value function to stay conservative such that out-of-distribution (OOD) actions will not be severely overestimated. However, existing approaches, penalizing the unseen actions or regularizing with the behavior policy, are too pessimistic, which suppresses the generalization of the value function and hinders the performance improvement. This paper explores mild but enough conservatism for offline learning while not harming generalization. We propose Mildly Conservative Q-learning (MCQ), where OOD actions are actively trained by assigning them proper pseudo Q values. We theoretically show that MCQ induces a policy that behaves at least as well as the behavior policy and no erroneous overestimation will occur for OOD actions. Experimental results on the D4RL benchmarks demonstrate that MCQ achieves remarkable performance compared with prior work. Furthermore, MCQ shows superior generalization ability when transferring from offline to online, and significantly outperforms baselines. Our code is publicly available at https://github.com/dmksjfl/MCQ.
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.
Syntology holds a reference implementation of Mildly Conservative Q-learning (MCQ), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Mildly Conservative Q-learning (MCQ)') (how to connect); the free check have('2206.04745') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2206.04745")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2206.04745", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2206.04745")
Code
The archive's official repository (dmksjfl/mcq) was not harvested; the 16 samples below come from 5 repositories the archive does not mark official.
Syntology 16 code samples harvested from 5 repositories linked to this paper: 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. 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): 9 samples from 2 repositories, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 7 samples from 3 repositories, 6 ran (5 with no instrument failure; 1 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 2 of its repositories that Syntology harvested for other papers:
- aviralkumar2907/CQL, found in paper text by Syntology: 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.
- sfujim/BCQ, found in paper text by Syntology: 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.
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
16 samples harvested: 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. “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: 11 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 5 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.
663ed93e901a35d7 · report
fixture: returned BasePolicy · level recorded 2026-09-22 a48659302894ea24 · report
fixture: signature batch:dict/0/? · returned dict · level recorded 2026-09-24 dc68158024e10b9e · report
55a4cdf8fa60dd90 · report
fixture: returned Actor · level recorded 2026-09-22 3e918e2e02356ef9 · report
fixture: returned ConditionalVAE · level recorded 2026-09-22 3bc3e8876aab07e5 · report
fixture: returned EnsembledCritic · level recorded 2026-09-22 5e14d0cf57ccbeb6 · report
fixture: returned EnsembledLinear · level recorded 2026-09-22 64e2c29dbb3226d9 · report
fixture: returned mcq_config · level recorded 2026-09-22 6dc14f1205c31904 · report
fixture: signature log_dict:dict/0/?, prefix:str/0/str, divider:str/0/str · returned OrderedDict · level recorded 2026-09-25 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 a5d10a0b704c8db7 · report
fixture: signature paths:list/1/dict · returned float64 · level recorded 2026-09-24 5cb0c55f58279f59 · report
fixture: signature separator:str/0/str · returned TableFormat · level recorded 2026-09-24 46e6d80fdfab6884 · report
6cb4331339777e6b · report
fixture: signature replay_buffer:MockReplayBuffer/0/?, batch_size:int/0/int · returned NoneType · level recorded 2026-09-24 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket critic.py ran · violated contract MIT (permissive) ·
13df74f8d96dca61 · report
fixture: signature diff:ArrayImpl/1/float, expectile:float/0/float · returned ArrayImpl · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
5 assemblies on this paper: 4 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).
generated Assembly for Mildly Conservative Q-learning (MCQ) (graph method: Mildly Conservative Q-learning (MCQ)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).
label matches by construction: the code was generated for this method (not judged by a model)
- mcq_critic_loss entry · level 3 · ran · honoured contract ·
837b283431e46db7c948c0695952516e7b79f7abbd957687e92f5936c0972466
4 sibling assemblies for Mildly Conservative Q-learning (MCQ) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Mildly Conservative Q-learning (MCQ) (graph method: Mildly Conservative Q-learning (MCQ)). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- loss entry · level 1 · ran · violated contract ·
13df74f8d96dca61
harvested Assembly for Mildly Conservative Q-learning (MCQ) (graph method: Mildly Conservative Q-learning (MCQ)). 6 bricks; individually on a fixture: 5 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 4 siblings
- MCQ entry · level 0 · unverified ·
99e3be0ffb010eef - Actor model · level 1 · ran ·
55a4cdf8fa60dd90 - ConditionalVAE model · level 1 · ran ·
3e918e2e02356ef9 - EnsembledCritic model · level 1 · ran ·
3bc3e8876aab07e5 - mcq_config helper · level 1 · ran ·
64e2c29dbb3226d9 - EnsembledLinear helper · level 1 · ran ·
5e14d0cf57ccbeb6
harvested Assembly for Mildly Conservative Q-learning (MCQ) (graph method: Mildly Conservative Q-learning (MCQ)). 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 4 siblings
- MCQPolicy entry · level 0 · unverified ·
dc68158024e10b9e - SACPolicy helper · level 1 · ran ·
a48659302894ea24 - BasePolicy helper · level 1 · ran ·
663ed93e901a35d7
harvested Assembly for Mildly Conservative Q-learning (MCQ) (graph method: Mildly Conservative Q-learning (MCQ)). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 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 4 siblings
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="2206.04745") 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
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