Papers › The MAGICAL Benchmark for Robust Imitation

The MAGICAL Benchmark for Robust Imitation

1 Nov 2020NeurIPS 2020 12arXiv:2011.00401archive 2025-07-28

Sam Toyer, Rohin Shah, Andrew Critch, Stuart Russell

Imitation Learning (IL) algorithms are typically evaluated in the same environment that was used to create demonstrations. This rewards precise reproduction of demonstrations in one particular environment, but provides little information about how robustly an algorithm can generalise the demonstrator's intent to substantially different deployment settings. This paper presents the MAGICAL benchmark suite, which permits systematic evaluation of generalisation by quantifying robustness to different kinds of distribution shift that an IL algorithm is likely to encounter in practice. Using the MAGICAL suite, we confirm that existing IL algorithms overfit significantly to the context in which demonstrations are provided. We also show that standard methods for reducing overfitting are effective at creating narrow perceptual invariances, but are not sufficient to enable transfer to contexts that require substantially different behaviour, which suggests that new approaches will be needed in order to robustly generalise demonstrator intent. Code and data for the MAGICAL suite is available at https://github.com/qxcv/magical/.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2011.00401")

Code

Syntology Ran 0 of 10 code samples harvested from 1 repository linked to this paper; 10 have no recorded run.

By repository: official repository: 10 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.

qxcv/magical officialmentioned in papermentioned on GitHubpytorchISC 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; 0 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

10unverified

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 qxcv/magical. “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.

darken_rgb qxcv/magical/magical/style.py official repository unverified ISC (permissive) · 6009fc6a277441d3 · report
get_display qxcv/magical/magical/gym_render.py official repository unverified ISC (permissive) · 9787f11078da23f3 · report
get_unique_fn qxcv/magical/magical/__main__.py official repository unverified ISC (permissive) · affa8da28334940f · report
latexify_results qxcv/magical/magical/evaluation.py official repository unverified ISC (permissive) · 6d496932d2281447 · report
lighten_rgb qxcv/magical/magical/style.py official repository unverified ISC (permissive) · 2d34512f6bbd54b5 · report
make_circle qxcv/magical/magical/gym_render.py official repository unverified ISC (permissive) · ca242cebfe737210 · report
regular_poly_apothem_to_side_legnth qxcv/magical/magical/geom.py official repository unverified ISC (permissive) · 9995efb7b9dd9a25 · report
regular_poly_circ_rad_to_side_length qxcv/magical/magical/geom.py official repository unverified ISC (permissive) · 042770b0f4e8a0c0 · report
regular_poly_circumrad qxcv/magical/magical/geom.py official repository unverified ISC (permissive) · c5ceb3580b3286f5 · report
rgb qxcv/magical/magical/style.py official repository unverified ISC (permissive) · 4010fcbb54d3f347 · report

Tasks

Imitation 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