SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.01207 · 2020

$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 1 failure of our instrument; 2 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/2010.01207.json · badge: /api/ran/2010.01207.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
fGAIL3456/fGAIL canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_cov_a Ran
ran on a synthesized input
fGAIL3456/fGAIL/a2c_ppo_acktr/algo/kfac.py
code served (permissive licence) · get_code("6aff48ec0d1463e1")
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 2, dtype family float, shape (27, 27) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import torch.nn as nn

torch.manual_seed(0)

# For Conv2d case: a should be a 4D tensor (batch, channels, height, width)
# layer_info should be (kernel_size, stride, padding)
# fast_cnn is a boolean

# Construct a small Conv2d input tensor
# batch_size=2, channels=3, height=5, width=5
a_conv2d = torch.randn(2, 3, 5, 5)

# layer_info for Conv2d: (kernel_size, stride, padding)
# kernel_size is a tuple (h, w)
# stride is a tuple (h, w)
# padding is a tuple (h, w)
layer_info_conv2d = ((3, 3), (1, 1), (1, 1))

# For AddBias case: a should be a tensor with size(0) as batch dimension
a_addbias = torch.randn(2, 4)

# Test parameters for Conv2d with fast_cnn=True
ARGS_conv2d_fast = {
    'a': a_conv2d,
    'classname': 'Conv2d',
    'layer_info': layer_info_conv2d,
    'fast_cnn': True
}

# Test parameters for Conv2d with fast_cnn=False
ARGS_conv2d_slow = {
    'a': a_conv2d,
    'classname': 'Conv2d',
    'layer_info': layer_info_conv2d,
    'fast_cnn': False
}

# Test parameters for AddBias
ARGS_addbias = {
    'a': a_addbias,
    'classname': 'AddBias',
    'layer_info': None,
    'fast_cnn': False
}

# Use the Conv2d fast case as the primary test
ARGS = ARGS_conv2d_fast
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 2, dtype family float, shape (27, 27) — shape (27, 27) 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_cov_g Ran
ran on a synthesized input
fGAIL3456/fGAIL/a2c_ppo_acktr/algo/kfac.py
code served (permissive licence) · get_code("d9fd61d47e236b09")
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 2, dtype family float, shape (4, 4) 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
import torch.nn as nn

torch.manual_seed(0)

# For Conv2d case: g needs shape (batch_size, channels, height, width)
# For AddBias case: g needs shape (batch_size, features, spatial_dims)
# For fast_cnn=True: g.view(batch, channels, -1) then sum(-1) -> (batch, channels)
# For fast_cnn=False: transpose and view operations

# Create a small gradient tensor for Conv2d
batch_size = 2
channels = 4
height = 3
width = 3

# Test with Conv2d classname and fast_cnn=True
g_conv2d_fast = torch.randn(batch_size, channels, height, width)

# For AddBias, need (batch_size, features, spatial_dims)
g_addbias = torch.randn(batch_size, 5, 6)

# layer_info is accessed but not used in the function body
layer_info = {}

ARGS = {
    "g": g_conv2d_fast,
    "classname": "Conv2d",
    "layer_info": layer_info,
    "fast_cnn": True,
}
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 2, dtype family float, shape (4, 4) — shape (4, 4) 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
merge Ran
ran; our contract draft was wrong, not the code
fGAIL3456/fGAIL/a2c_ppo_acktr/model_utils.py
code served (permissive licence) · get_code("2d15f050207aff53")
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 2, dtype family float, shape (2, 7) 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)

# The merge function concatenates two tensors along dimension 1
# It expects two tensors x1 and x2
# We'll create small tensors with distinct shapes to make debugging easier

x1 = torch.randn(2, 3)  # batch size 2, feature dim 3
x2 = torch.randn(2, 4)  # batch size 2, feature dim 4

ARGS = {
    "x1": x1,
    "x2": x2,
}
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 2, dtype family float, shape (2, 7) — shape (2, 7) 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
process_maxmin_groupsize Ran
ran on a synthesized input
fGAIL3456/fGAIL/a2c_ppo_acktr/model_utils.py
code served (permissive licence) · get_code("3ffb195b7f9d2a6a")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - x: needs to have a .size() method that returns a sequence, and support indexing
#      This is a torch.Tensor
# - group_size: an integer that divides num_channels evenly
# - axis: an integer (default -1), used for indexing into size list

# Create a small tensor with shape (2, 4, 3, 8)
# Using distinct sizes for clarity
x = torch.randn(2, 4, 3, 8)

# group_size: must divide the size along the axis evenly
# For axis=-1 (default), num_channels = 8, so group_size could be 2, 4, or 8
group_size = 2

# axis: default is -1, let's test with that
axis = -1

ARGS = {
    "x": x,
    "group_size": group_size,
    "axis": axis
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
split Ran
ran on a synthesized input
fGAIL3456/fGAIL/a2c_ppo_acktr/model_utils.py
code served (permissive licence) · get_code("f31c6c36e11645e2")
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 tuple, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# The function `split` takes a tensor x and splits it along dimension 1 (the second dimension)
# It expects x to have shape (batch, channels, height, width) based on the indexing operations
# x.size(1) gets the second dimension, which is split in half

# Create a small 4D tensor: (batch=2, channels=4, height=3, width=5)
x = torch.randn(2, 4, 3, 5)

ARGS = {
    "x": x
}
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 tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
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
power_series_full_jac_exact_trace Not yet run
unverified (harvested, no recorded run)
fGAIL3456/fGAIL/a2c_ppo_acktr/matrix_utils.py
code served (permissive licence) · get_code("8a3ac7de797e022f")
How it ran

no invocation recorded.

power_series_matrix_logarithm_trace Not yet run
unverified (harvested, no recorded run)
fGAIL3456/fGAIL/a2c_ppo_acktr/matrix_utils.py
code served (permissive licence) · get_code("ff79b75e8d4e8e73")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 4 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
compute_cov_a 8 other papers
6 dated earlier, 2 later
1803.01273 (2018-03)
Accelerating Natural Gradient with Higher-Order Invariance
1806.05635 (2018-06)
Self-Imitation Learning
1903.04110 (2019-03)
Hybrid Reinforcement Learning with Expert State Sequences
and 5 more not named here
compute_cov_g 8 other papers
6 dated earlier, 2 later
1803.01273 (2018-03)
Accelerating Natural Gradient with Higher-Order Invariance
1806.05635 (2018-06)
Self-Imitation Learning
1903.04110 (2019-03)
Hybrid Reinforcement Learning with Expert State Sequences
and 5 more not named here
merge 2 other papers
1 dated earlier, 1 later
1802.07088 (2018-02)
i-RevNet: Deep Invertible Networks
2308.04699 (2023-08)
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

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

Imitation learning (IL) aims to learn a policy from expert demonstrations that minimizes the discrepancy between the learner and expert behaviors. Various imitation learning algorithms have been proposed with different pre-determined divergences to quantify the discrepancy. This naturally gives rise to the following question: Given a set of expert demonstrations, which divergence can recover the expert policy more accurately with higher data efficiency? In this work, we propose $f$-GAIL, a new generative adversarial imitation learning (GAIL) model, that automatically learns a discrepancy measure from the $f$-divergence family as well as a policy capable of producing expert-like behaviors. Compared with IL baselines with various predefined divergence measures, $f$-GAIL learns better policies with higher data efficiency in six physics-based control tasks.

For agents

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

get_harvested_code_for_paper("2010.01207")
get_code_for_paper("2010.01207")
have("2010.01207")

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

curl https://syntology.ai/api/ran/2010.01207.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.01207.svg)](https://syntology.ai/paper/2010.01207)

Connect an agent — have() is free.