Papers › Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models

Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models

4 Dec 2023NeurIPS 2023 11arXiv:2312.02019archive 2025-07-28

Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl

Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely observing and imitating others. This ability highly depends on the fact that humans have a model of their own embodiment that allows them to infer the most likely actions that led to the observed behaviour. In this paper, we propose Action Inference by Maximising Evidence (AIME) to replicate this behaviour using world models. AIME consists of two distinct phases. In the first phase, the agent learns a world model from its past experience to understand its own body by maximising the ELBO. While in the second phase, the agent is given some observation-only demonstrations of an expert performing a novel task and tries to imitate the expert's behaviour. AIME achieves this by defining a policy as an inference model and maximising the evidence of the demonstration under the policy and world model. Our method is "zero-shot" in the sense that it does not require further training for the world model or online interactions with the environment after given the demonstration. We empirically validate the zero-shot imitation performance of our method on the Walker and Cheetah embodiment of the DeepMind Control Suite and find it outperforms the state-of-the-art baselines. Code is available at: https://github.com/argmax-ai/aime.

PaperPDFConference PDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 11 ran (11 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

argmax-ai/aime officialmentioned in paperpytorchSyntology: 13 samples, 11 ran (0 instrument-failed) · 2 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

13 samples harvested: 11 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

11ran
2unverified

Licence: 13 of the 13 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 argmax-ai/aime. “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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

argmax-ai/aime official repository 13 samples, 11 ran (0 instrument-failed) · 2 unverified
ArrayDict aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 054a626c432b8b0d · report fixture: returned ArrayDict · level recorded 2026-09-22
CNNDecoderHa aime/models/ssm.py ran licence not identified · pointer only · 8093a28c0da72045 · report fixture: signature state:Tensor/2/float · returned Normal · level recorded 2026-09-24
CNNEncoderHa aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 0236a316f55034f1 · report fixture: returned CNNEncoderHa · level recorded 2026-09-22
IndentityEncoder aime/models/ssm.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 3f256b19ea8a8d30 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MLP in 375 papers aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · e969ad6f6aca286e · report fixture: returned MLP · level recorded 2026-09-22
MLPDeterministicDecoder aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 195cf65a858408ff · report fixture: returned MLPDeterministicDecoder · level recorded 2026-09-22
MLPStaticStochasticDecoder aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 8f41c62efab438ce · report fixture: returned MLPStaticStochasticDecoder · level recorded 2026-09-22
MLPStochasticDecoder aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 5ffb55ea7a43b5a0 · report fixture: returned MLPStochasticDecoder · level recorded 2026-09-22
Normal in 11 papers aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 828f62980511fb44 · report fixture: returned Normal · level recorded 2026-09-22
TanhGaussianPolicy in 6 papers aime/models/ssm.py ran · metamorphic tier: deterministic licence not identified · pointer only · 802c8c98d4863016 · report fixture: returned TanhGaussianPolicy · level recorded 2026-09-22
TanhNormal aime/models/ssm.py ran licence not identified · pointer only · 2ad60a490c179619 · report fixture: returned TanhNormal · level recorded 2026-09-22
RSSM in 7 papers aime/models/ssm.py unverified licence not identified · pointer only · 518be015fb96eae9 · report
SSM in 5 papers aime/models/ssm.py unverified licence not identified · pointer only · b8c98261c7e37217 · 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 Action Inference by Maximising Evidence (AIME) (graph method: Action Inference by Maximising Evidence (AIME)). 13 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. RSSM entry · level 0 · unverified · 518be015fb96eae9
  2. ArrayDict helper · level 1 · ran · 054a626c432b8b0d
  3. MLP helper · level 1 · ran · e969ad6f6aca286e
  4. Normal helper · level 1 · ran · 828f62980511fb44
  5. SSM model · level 0 · unverified · b8c98261c7e37217
  6. TanhGaussianPolicy model · level 1 · ran · 802c8c98d4863016
  7. TanhNormal helper · level 1 · ran · 2ad60a490c179619
  8. CNNDecoderHa model · level 1 · ran · 8093a28c0da72045
  9. CNNEncoderHa model · level 1 · ran · 0236a316f55034f1
  10. IndentityEncoder helper · level 1 · ran · 3f256b19ea8a8d30
  11. MLPDeterministicDecoder model · level 1 · ran · 195cf65a858408ff
  12. MLPStaticStochasticDecoder helper · level 1 · ran · 8f41c62efab438ce
  13. MLPStochasticDecoder model · level 1 · ran · 5ffb55ea7a43b5a0

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="2312.02019") returns these assemblies with each brick's role and wiring (how to connect).

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