Papers › Is Value Learning Really the Main Bottleneck in Offline RL?

Is Value Learning Really the Main Bottleneck in Offline RL?

13 Jun 2024arXiv:2406.09329archive 2025-07-28

Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar

While imitation learning requires access to high-quality data, offline reinforcement learning (RL) should, in principle, perform similarly or better with substantially lower data quality by using a value function. However, current results indicate that offline RL often performs worse than imitation learning, and it is often unclear what holds back the performance of offline RL. Motivated by this observation, we aim to understand the bottlenecks in current offline RL algorithms. While poor performance of offline RL is typically attributed to an imperfect value function, we ask: is the main bottleneck of offline RL indeed in learning the value function, or something else? To answer this question, we perform a systematic empirical study of (1) value learning, (2) policy extraction, and (3) policy generalization in offline RL problems, analyzing how these components affect performance. We make two surprising observations. First, we find that the choice of a policy extraction algorithm significantly affects the performance and scalability of offline RL, often more so than the value learning objective. For instance, we show that common value-weighted behavioral cloning objectives (e.g., AWR) do not fully leverage the learned value function, and switching to behavior-constrained policy gradient objectives (e.g., DDPG+BC) often leads to substantial improvements in performance and scalability. Second, we find that a big barrier to improving offline RL performance is often imperfect policy generalization on test-time states out of the support of the training data, rather than policy learning on in-distribution states. We then show that the use of suboptimal but high-coverage data or test-time policy training techniques can address this generalization issue in practice. Specifically, we propose two simple test-time policy improvement methods and show that these methods lead to better performance.

PaperPDFCodeCode 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

Syntology 10 code samples harvested from 1 repository linked to this paper: 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 10 samples from 1 repository, 7 ran (7 with no instrument failure; 0 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.

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

seohongpark/ogbench mentioned on GitHubjaxSyntology: 10 samples, 7 ran (0 instrument-failed) · 3 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.

Code Syntology ran Syntology

10 samples harvested: 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 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.

7ran
3unverified

Licence: 0 of the 10 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 seohongpark/ogbench. “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”. “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.

seohongpark/ogbench community (archive-listed) 10 samples, 7 ran (0 instrument-failed) · 3 unverified
GCActor impls/agents/hiql.py ran MIT (permissive) · 9bc539476ffcf222 · report fixture: returned GCActor · level recorded 2026-09-22
GCEncoder impls/agents/hiql.py ran MIT (permissive) · 85c24c360661275c · report fixture: returned GCEncoder · level recorded 2026-09-22
GCValue impls/agents/hiql.py ran MIT (permissive) · 1a0dd970d5292061 · report fixture: returned GCValue · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
impls/agents/hiql.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 55eac5ab51a6832f · report fixture: signature x:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22
ImpalaEncoder in 6 papers impls/agents/hiql.py ran MIT (permissive) · 503831beac2bf3d9 · report fixture: returned ImpalaEncoder · level recorded 2026-09-22
MLP in 375 papers impls/agents/hiql.py ran MIT (permissive) · ccbb1f2bba20397b · report fixture: returned MLP · level recorded 2026-09-22
ModuleDict in 6 papers impls/agents/hiql.py ran MIT (permissive) · 1b4a14ceaf967da5 · report fixture: returned ModuleDict · level recorded 2026-09-22
GCDiscreteActor impls/agents/hiql.py unverified MIT (permissive) · 76e656aaad5ce115 · report
HIQLAgent impls/agents/hiql.py unverified MIT (permissive) · 3c394762e2a85d6f · report
LengthNormalize impls/agents/hiql.py unverified MIT (permissive) · 2c53e405a504fd6d · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for test-time policy improvement methods (graph method: test-time policy improvement methods). 15 bricks; individually on a fixture: 11 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. HIQLAgent entry · level 0 · unverified · 3c394762e2a85d6f
  2. GCActor helper · level 1 · ran · 9bc539476ffcf222
  3. GCDiscreteActor helper · level 0 · unverified · 76e656aaad5ce115
  4. GCEncoder helper · level 1 · ran · 85c24c360661275c
  5. GCValue helper · level 1 · ran · 1a0dd970d5292061
  6. Identity helper · level 1 · ran · 55eac5ab51a6832f
  7. LengthNormalize helper · level 0 · unverified · 2c53e405a504fd6d
  8. MLP helper · level 1 · ran · ccbb1f2bba20397b
  9. ModuleDict helper · level 1 · ran · 1b4a14ceaf967da5
  10. TrainState helper · level 1 · ran · 320b57aeb460d8c6
  11. TransformedWithMode helper · level 0 · unverified · f12c586742efe2f1
  12. default_init helper · level 1 · ran · our draft was wrong · 2aaa6f4e0d62bf22
  13. ensemblize helper · level 1 · ran · our draft was wrong · e2b6e84f73d1d030
  14. ImpalaEncoder helper · level 1 · ran · 503831beac2bf3d9
  15. ResnetStack helper · level 1 · ran · 6a774c1075ea7123

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="2406.09329") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Imitation LearningOffline RLReinforcement Learning (RL)

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