SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.02256 · 2019

A Divergence Minimization Perspective on Imitation Learning Methods

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 0 have no contract verdict; 2 failures of our instrument; 1 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/1911.02256.json · badge: /api/ran/1911.02256.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
KamyarGh/rl_swiss extension (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_spherical_log_prob Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KamyarGh/rl_swiss/neural_processes/neural_process.py
code served (permissive licence) · get_code("682916998c15956a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct valid arguments for compute_spherical_log_prob
preds = torch.randn(2, 4)  # batch_size=2, dim=4
true_outputs = torch.randn(2, 4)  # same shape as preds
mask = torch.ones(2, 4)  # binary mask, same shape as preds and true_outputs
n_samples = 5  # number of samples

ARGS = {
    "preds": preds,
    "true_outputs": true_outputs,
    "mask": mask,
    "n_samples": n_samples
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
logsumexp Ran
ran; our contract draft was wrong, not the code
KamyarGh/rl_swiss/neural_processes/neural_process.py
code served (permissive licence) · get_code("a4b037b438505679")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with shape (2, 4) for testing
inputs = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    "inputs": inputs,
    "dim": 1,
    "keepdim": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_diag_log_prob Not yet run
unverified (harvested, no recorded run)
KamyarGh/rl_swiss/neural_processes/neural_process.py
code served (permissive licence) · get_code("36a31aa01dc3a480")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
logsumexp 9 other papers
1 dated earlier, 8 later
1906.02771 (2019-06)
Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
2004.14451 (2020-04)
Pragmatic Issue-Sensitive Image Captioning
2010.08830 (2020-10)
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
and 6 more not named here

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

In many settings, it is desirable to learn decision-making and control policies through learning or bootstrapping from expert demonstrations. The most common approaches under this Imitation Learning (IL) framework are Behavioural Cloning (BC), and Inverse Reinforcement Learning (IRL). Recent methods for IRL have demonstrated the capacity to learn effective policies with access to a very limited set of demonstrations, a scenario in which BC methods often fail. Unfortunately, due to multiple factors of variation, directly comparing these methods does not provide adequate intuition for understanding this difference in performance. In this work, we present a unified probabilistic perspective on IL algorithms based on divergence minimization. We present $f$-MAX, an $f$-divergence generalization of AIRL [Fu et al., 2018], a state-of-the-art IRL method. $f$-MAX enables us to relate prior IRL methods such as GAIL [Ho & Ermon, 2016] and AIRL [Fu et al., 2018], and understand their algorithmic properties. Through the lens of divergence minimization we tease apart the differences between BC and successful IRL approaches, and empirically evaluate these nuances on simulated high-dimensional continuous control domains. Our findings conclusively identify that IRL's state-marginal matching objective contributes most to its superior performance. Lastly, we apply our new understanding of IL methods to the problem of state-marginal matching, where we demonstrate that in simulated arm pushing environments we can teach agents a diverse range of behaviours using simply hand-specified state distributions and no reward functions or expert demonstrations. For datasets and reproducing results please refer to https://github.com/KamyarGh/rl_swiss/blob/master/reproducing/fmax_paper.md .

For agents

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

get_harvested_code_for_paper("1911.02256")
get_code_for_paper("1911.02256")
have("1911.02256")

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

curl https://syntology.ai/api/ran/1911.02256.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.02256.svg)](https://syntology.ai/paper/1911.02256)

Connect an agent — have() is free.