Papers › Video Prediction Models as Rewards for Reinforcement Learning

Video Prediction Models as Rewards for Reinforcement Learning

23 May 2023NeurIPS 2023 11arXiv:2305.14343archive 2025-07-28

Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for behaviors from unlabeled videos, which are widely available on the internet. We present Video Prediction Rewards (VIPER), an algorithm that leverages pretrained video prediction models as action-free reward signals for reinforcement learning. Specifically, we first train an autoregressive transformer on expert videos and then use the video prediction likelihoods as reward signals for a reinforcement learning agent. VIPER enables expert-level control without programmatic task rewards across a wide range of DMC, Atari, and RLBench tasks. Moreover, generalization of the video prediction model allows us to derive rewards for an out-of-distribution environment where no expert data is available, enabling cross-embodiment generalization for tabletop manipulation. We see our work as starting point for scalable reward specification from unlabeled videos that will benefit from the rapid advances in generative modeling. Source code and datasets are available on the project website: https://escontrela.me/viper

PaperPDFConference PDFCodeCode Syntology ran

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 15 code samples: 14 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 15: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 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): 14 samples from 2 repositories, 11 ran (7 with no instrument failure; 4 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.

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. 1 of the 12 samples that ran has no recorded date.

Alescontrela/viper_rl mentioned on GitHubjaxMITSyntology: 11 samples, 9 ran (3 instrument-failed) · 2 unverified report
alescontrela/viper mentioned on GitHubjaxMITSyntology: not harvested report
nyuolab/VIPER-torch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 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.

2ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
6ran
3unverified

Licence: 1 of the 15 samples is 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 2 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”. “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.

Alescontrela/viper_rl community (archive-listed) 11 samples, 9 ran (3 instrument-failed) · 2 unverified
cast_to_compute in 7 papers viper_rl/dreamerv3/jaxutils.py ran · our draft was wrong MIT (permissive) · 24fe13b4f847da6b · report fixture: signature values:dict/0/? · returned dict · level recorded 2026-09-24
gelu2 viper_rl/videogpt/models/transformer.py ran fingerprinted MIT (permissive) · f22419e1c6850259 · report fixture: signature x:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
get_act in 56 papers viper_rl/dreamerv3/nets.py ran · our draft was wrong MIT (permissive) · 03dd934385b4d240 · report fixture: signature name:str/0/str · returned custom_jvp · level recorded 2026-09-25
load_npz in 17 papers viper_rl/videogpt/data.py ran MIT (permissive) · 3420673d38aa9a45 · report fixture: signature config:Config/0/?, data_path:str/0/str, train:bool/0/bool, n_shards:int/0/int, shard_id:int/0/int, mask:ndarray/2/float · returned _MapDataset · level recorded 2026-09-25
minibatch_stddev_layer viper_rl/videogpt/models/stylegan_disc.py ran MIT (permissive) · 9482258884b8a214 · report fixture: signature x:ArrayImpl/4/float, group_size:int/0/int, num_new_features:int/0/int, is_initializing:bool/0/bool · returned ArrayImpl · level recorded 2026-09-25
prepare in 17 papers viper_rl/videogpt/data.py ran MIT (permissive) · d189db7683bb8237 · report fixture: signature dataset:_TensorSliceDataset/0/?, batch_size:int/0/int, initial_shape:tuple/1/int · returned map · level recorded 2026-09-24
pure in 7 papers viper_rl/dreamerv3/ninjax.py ran MIT (permissive) · 5f596558510431da · report fixture: signature fun:callable/0/?, nested:bool/0/bool · returned function · level recorded 2026-09-24
subsample in 25 papers viper_rl/dreamerv3/jaxutils.py ran MIT (permissive) · e5b1910ea05891b1 · report fixture: signature values:ArrayImpl/2/float, amount:int/0/int · returned ArrayImpl · level recorded 2026-09-24
tensorstats in 10 papers viper_rl/dreamerv3/jaxutils.py ran; the contract check could not run (RAISES) MIT (permissive) · 67c6d2355562342f · report fixture: signature tensor:ArrayImpl/2/float, prefix:str/0/str · returned dict · level recorded 2026-09-24
grad in 23 papers viper_rl/dreamerv3/ninjax.py unverified MIT (permissive) · afd5fe78d3d65a81 · report
rng in 7 papers viper_rl/dreamerv3/ninjax.py unverified MIT (permissive) · a03f3f2133e3fcee · report
nyuolab/VIPER-torch community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
extract_iteration scripts/train_vqgan.py ran · honoured contract fingerprinted MIT (permissive) · 688edacb9a7e28a4 · report fixture: signature filename:str/0/str · returned int · level recorded 2026-09-22
train_step in 47 papers scripts/train_vqgan.py ran · our draft was wrong MIT (permissive) · 1afd8c944e46c401 · report fixture: signature batch:dict/0/?, state:State/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
train_step in 47 papers scripts/train_videogpt.py unverified MIT (permissive) · ecce8632ff15a248 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
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.
count_steps in 9 papers repository not located ran · honoured contract licence of this copy not recorded · b7ff9ef9697d35f1 · report fixture: signature folder:PosixPath/0/? · returned int · level recorded, date not recorded

Tasks

PredictionReinforcement LearningVideo Predictionreinforcement-learning

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