Papers › RvS: What is Essential for Offline RL via Supervised Learning?

RvS: What is Essential for Offline RL via Supervised Learning?

20 Dec 2021arXiv:2112.10751archive 2025-07-28

Scott Emmons, Benjamin Eysenbach, Ilya Kostrikov, Sergey Levine

Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. When does this hold true, and which algorithmic components are necessary? Through extensive experiments, we boil supervised learning for offline RL down to its essential elements. In every environment suite we consider, simply maximizing likelihood with a two-layer feedforward MLP is competitive with state-of-the-art results of substantially more complex methods based on TD learning or sequence modeling with Transformers. Carefully choosing model capacity (e.g., via regularization or architecture) and choosing which information to condition on (e.g., goals or rewards) are critical for performance. These insights serve as a field guide for practitioners doing Reinforcement Learning via Supervised Learning (which we coin "RvS learning"). They also probe the limits of existing RvS methods, which are comparatively weak on random data, and suggest a number of open problems.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2112.10751")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: official repository: 9 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

scottemmons/rvs officialmentioned in papermentioned on GitHubpytorchMIT 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

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9unverified

Licence: 0 of the 9 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 scottemmons/rvs. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

aggregate_performance scottemmons/rvs/src/rvs/visualize.py official repository unverified MIT (permissive) · e2168f17c792e370 · report
configure_gpu scottemmons/rvs/src/rvs/util.py official repository unverified MIT (permissive) · 904308085f6cca90 · report
extract_done_markers scottemmons/rvs/src/rvs/util.py official repository unverified MIT (permissive) · 8b1664741c54346a · report
extract_traj_markers scottemmons/rvs/src/rvs/util.py official repository unverified MIT (permissive) · 0bab79bd43ebf743 · report
get_total_steps scottemmons/rvs/src/rvs/step.py official repository unverified MIT (permissive) · 6aefaad3876d1cda · report
is_kitchen_env scottemmons/rvs/src/rvs/step.py official repository unverified MIT (permissive) · 092e8da61aa4b415 · report
load_rollouts scottemmons/rvs/src/rvs/step.py official repository unverified MIT (permissive) · 408460ecefee36fd · report
make_s_g_tensor scottemmons/rvs/src/rvs/dataset.py official repository unverified MIT (permissive) · 864394f1eb93272b · report
to_tensor_dataset scottemmons/rvs/src/rvs/dataset.py official repository unverified MIT (permissive) · 459c8b306f2c2123 · report

Tasks

Offline 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