SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.03525 · 2020

Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 1 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2008.03525.json · badge: /api/ran/2008.03525.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
OlegArenz/O-NAIL canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
boolean_string Ran
ran, violated the contract we drafted
OlegArenz/O-NAIL/common/utlis.py
pointer only (licence: MIT); the stored copy get_code serves, from PruneTruong/GOCor, is pointer only (licence: NOASSERTION) · get_code("b1f9cebf0d177140")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from PruneTruong/GOCor, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

build_kwargs_from_command_line_args Ran
ran on a synthesized input
OlegArenz/O-NAIL/run_experiment.py
code served (permissive licence) · get_code("7ab6586c15485b41")
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 1, 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 numpy as np

class MockArgs:
    """Mock args object with command-line style parameters"""
    def __init__(self):
        self.il_learning_rate = 0.001
        self.il_batch_size = 32
        self.il_epochs = 10
        self.policy_hidden_dim = 128
        self.policy_activation = 'relu'
        self.policy_num_layers = 2
        self.Q_hidden_dim = 64
        self.Q_learning_rate = 0.0005
        self.unrelated_param = 'should_not_appear'

ARGS = {
    'args': MockArgs()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
process_trajectories Ran
ran on a synthesized input
OlegArenz/O-NAIL/common/utlis.py
code served (permissive licence) · get_code("7f3c670f6150299c")
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. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np
import tensorflow as tf

# Create sample trajectory data
# Each trajectory is a 2D array where:
# - First num_states columns are states
# - Remaining columns are actions

num_states = 3
num_actions = 2

# Create 2 trajectories with 5 timesteps each
# Shape: (5, num_states + num_actions) = (5, 5)
trajectory_1 = np.random.randn(5, num_states + num_actions).astype(np.float32)
trajectory_2 = np.random.randn(5, num_states + num_actions).astype(np.float32)

trajectories = [trajectory_1, trajectory_2]

ARGS = {
    "trajectories": trajectories,
    "num_states": num_states,
    "return_as_tensors": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
roll_out_policy Ran
ran on a synthesized input
OlegArenz/O-NAIL/common/utlis.py
code served (permissive licence) · get_code("22989ac3bf03e8a8")
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. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np
import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal policy that has a step method
class MinimalPolicy(nn.Module):
    def __init__(self, obs_dim=4, action_dim=3):
        super().__init__()
        self.linear = nn.Linear(obs_dim, action_dim)
    
    def step(self, obs, deterministic=False):
        # obs shape: (batch, obs_dim)
        # returns (action, ...) where action has shape (batch, action_dim)
        with torch.no_grad():
            obs_tensor = torch.tensor(obs, dtype=torch.float32)
            action = self.linear(obs_tensor).numpy()
        return (action,)

# Create a minimal environment that has reset, step, render methods
class MinimalEnv:
    def __init__(self, obs_dim=4, action_dim=3):
        self.obs_dim = obs_dim
        self.action_dim = action_dim
        self.step_count = 0
        self.max_steps = 3
        self.env = self
    
    def reset(self):
        self.step_count = 0
        return np.random.randn(self.obs_dim).astype(np.float32)
    
    def _get_obs(self):
        return np.random.randn(self.obs_dim).astype(np.float32)
    
    def step(self, action):
        # returns (obs, rewards, dones, info)
        self.step_count += 1
        obs = np.random.randn(self.obs_dim).astype(np.float32)
        rewards = float(np.random.randn())
        dones = self.step_count >= self.max_steps
        info = {}
        return (obs, rewards, dones, info)
    
    def render(self):
        pass

# Construct arguments
policy = MinimalPolicy(obs_dim=4, action_dim=3)
env = MinimalEnv(obs_dim=4, action_dim=3)

ARGS = {
    'env': env,
    'policy': policy,
    'max_episodes': 2,
    'max_samps': np.inf,
    'reset_env': True,
    'render': False,
    'deterministic': False,
}
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 tuple — a tuple output has no array shape of its own; none is stated
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 3 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
boolean_string 10 other papers
4 dated earlier, 6 later
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
1912.05524 (2019-12)
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
2006.11280 (2020-06)
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
and 7 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

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the implicit state-action distribution induced by the agent's policy. However, by framing imitation learning as a saddle point problem, adversarial methods can suffer from unstable optimization, and convergence can only be shown for small policy updates. We address these problems by proposing a framework for non-adversarial imitation learning. The resulting algorithms are similar to their adversarial counterparts and, thus, provide insights for adversarial imitation learning methods. Most notably, we show that AIRL is an instance of our non-adversarial formulation, which enables us to greatly simplify its derivations and obtain stronger convergence guarantees. We also show that our non-adversarial formulation can be used to derive novel algorithms by presenting a method for offline imitation learning that is inspired by the recent ValueDice algorithm, but does not rely on small policy updates for convergence. In our simulated robot experiments, our offline method for non-adversarial imitation learning seems to perform best when using many updates for policy and discriminator at each iteration and outperforms behavioral cloning and ValueDice.

For agents

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

get_harvested_code_for_paper("2008.03525")
get_code_for_paper("2008.03525")
have("2008.03525")

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

curl https://syntology.ai/api/ran/2008.03525.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.03525.svg)](https://syntology.ai/paper/2008.03525)

Connect an agent — have() is free.