SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.05698 · 2022

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2212.05698.json · badge: /api/ran/2212.05698.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
facebookresearch/modem canonical (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
cfg_to_group Ran
ran; our contract draft was wrong, not the code
facebookresearch/modem/logger.py
pointer only (licence: MIT) · get_code("d2c1837dcce6a2f6")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

enc Ran
ran on a synthesized input
facebookresearch/modem/algorithm/helper.py
pointer only (licence: MIT) · get_code("688316a579d8c8d1")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_state_dim Ran
ran on a synthesized input
facebookresearch/modem/tasks/dmcontrol.py
pointer only (licence: MIT) · get_code("029123dcb1fd1fa5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l1 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/modem/algorithm/helper.py
pointer only (licence: MIT) · get_code("9925b7e4eb50dcae")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_dir Ran
ran; our contract draft was wrong, not the code
facebookresearch/modem/logger.py
pointer only (licence: MIT) · get_code("436a7981ede1cf9d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_env Ran
ran on a synthesized input
facebookresearch/modem/env.py
pointer only (licence: MIT) · get_code("88d563b866d0550c")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/modem/algorithm/helper.py
pointer only (licence: MIT) · get_code("8d8f088c9186b5d4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_cfg Ran
ran on a synthesized input
facebookresearch/modem/cfg_parse.py
pointer only (licence: MIT) · get_code("a28e11143461d211")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_sim Not yet run
unverified (harvested, no recorded run)
facebookresearch/modem/tasks/mj_envs/mj_envs/envs/env_base.py
pointer only (licence: MIT) · get_code("e285ec81dccf7cb8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

make_adroit_env Not yet run
unverified (harvested, no recorded run)
facebookresearch/modem/tasks/adroit.py
pointer only (licence: MIT) · get_code("a9663bfb523e687a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

print_run Not yet run
unverified (harvested, no recorded run)
facebookresearch/modem/logger.py
pointer only (licence: MIT) · get_code("b308a8f7c164f9e5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/modem, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
make_dir 7 other papers
2 dated earlier, 5 later
2107.00644 (2021-07)
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
2210.07241 (2022-10)
Visual Reinforcement Learning with Self-Supervised 3D Representations
2312.15339 (2023-12)
MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning
and 4 more not named here
cfg_to_group 2 other papers
2 later
2605.16692 (2026-05)
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
2608.07870 (2026-08)
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
l1 2 other papers
2 later
2310.16828 (2023-10)
Scalable, Robust World Models for Continuous Control
2404.03037 (2024-04)
Model-based Reinforcement Learning for Parameterized Action Spaces
mse 2 other papers
2 later
2310.16828 (2023-10)
Scalable, Robust World Models for Continuous Control
2404.03037 (2024-04)
Model-based Reinforcement Learning for Parameterized Action Spaces

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly sample efficient by concurrently learning a world model and using synthetic rollouts for planning and policy improvement. However, in practice, sample-efficient learning with model-based RL is bottlenecked by the exploration challenge. In this work, we find that leveraging just a handful of demonstrations can dramatically improve the sample-efficiency of model-based RL. Simply appending demonstrations to the interaction dataset, however, does not suffice. We identify key ingredients for leveraging demonstrations in model learning -- policy pretraining, targeted exploration, and oversampling of demonstration data -- which forms the three phases of our model-based RL framework. We empirically study three complex visuo-motor control domains and find that our method is 150%-250% more successful in completing sparse reward tasks compared to prior approaches in the low data regime (100K interaction steps, 5 demonstrations). Code and videos are available at: https://nicklashansen.github.io/modemrl

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2212.05698")
get_code_for_paper("2212.05698")
have("2212.05698")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2212.05698.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2212.05698.svg)](https://syntology.ai/paper/2212.05698)

Connect an agent — have() is free.