Papers › Generative Adversarial Imitation Learning
Generative Adversarial Imitation Learning
Jonathan Ho, Stefano Ermon
Consider learning a policy from example expert behavior, without interaction with the expert or access to reinforcement signal. One approach is to recover the expert's cost function with inverse reinforcement learning, then extract a policy from that cost function with reinforcement learning. This approach is indirect and can be slow. We propose a new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning. We show that a certain instantiation of our framework draws an analogy between imitation learning and generative adversarial networks, from which we derive a model-free imitation learning algorithm that obtains significant performance gains over existing model-free methods in imitating complex behaviors in large, high-dimensional environments.
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):
get_harvested_code_for_paper(arxiv_id="1606.03476")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1606.03476", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1606.03476")
Code
Syntology 36 code samples harvested from 9 repositories linked to this paper: 24 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 36 samples from 9 repositories, 24 ran (22 with no instrument failure; 2 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.
No sample is linked to this paper from 7 of its repositories that Syntology harvested for other papers:
- 170928/-Review-Generative-Adversarial-Imitation-Learning, community (archive-listed): harvested for another paper, listed under the repository
- HumanCompatibleAI/deep-rlsp, community (archive-listed): harvested for another paper, listed under the repository
- Khrylx/PyTorch-RL, community (archive-listed): harvested for 3 other papers, listed under the repository
- ran-weii/cleanil, community (archive-listed): harvested for another paper, listed under the repository
- rohitrango/Reward-bias-in-GAIL, community (archive-listed): harvested for another paper, listed under the repository
- hill-a/stable-baselines, community (archive-listed): harvested for 2 other papers, listed under the repository
- opendilab/DI-engine, community (archive-listed): harvested for 4 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
18 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
36 samples harvested: 24 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 2 where Syntology's instrument failed) · 12 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.
Licence: 15 of the 36 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 5 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.
cf7c0b7b5de1e98b · report
fixture: signature agent:callable/0/?, current_Q:Tensor/2/float, current_v:Tensor/2/float, next_v:Tensor/2/float, batch:tuple/1/Tensor · returned tuple · level recorded 2026-09-22 0654ba2a385cf2c4 · report
4117e20071c70a04 · report
12a65e5d7d9e912d · report
5ce9c8b1227054f5 · report
343ea6d8bbc7b6dc · report
58c499108eff7753 · report
fixture: returned GAILDiscriminator · level recorded 2026-09-22 d0f9a51097534c31 · report
fixture: returned SoftActor · level recorded 2026-09-22 ee98cbfd5f8b7c6d · report
fixture: signature input_size:int/0/int, hidden_size:int/0/int, depth:int/0/int, output_size:int/0/int, activation_function:str/0/str, input_dropout:float/0/float, dropout:float/0/float, final_gain:float/0/float, spectral_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22 e374e2ee3dbb3f45 · report
fixture: signature state:Tensor/2/float, action:Tensor/2/float · returned Tensor · level recorded 2026-09-22 df69a6d635ac78ad · report
fixture: signature x_1:Tensor/2/float, x_2:Tensor/2/float, eps:Tensor/1/float · returned Tensor · level recorded 2026-09-22 71bdb8bae1ed81f7 · report
fixture: signature env_id:str/0/str · returned tuple · level recorded 2026-09-25 c45e54fc5355bc2d · report
fixture: signature param:ndarray/2/int · returned ndarray · level recorded 2026-09-26 af3d493bdc17ad51 · report
fixture: signature dir:str/0/str · returned list · level recorded 2026-09-26 3e82b9de30b1625f · report
fixture: signature benchmark:dict/0/?, env_id:str/0/str · returned dict · level recorded 2026-09-25 2e4f14f2d4a888ff · report
fixture: signature logits:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26 3032d5dbb694f8ba · report
fixture: signature a:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26 071e746ec3f03d74 · report
fixture: signature format:str/0/str, ev_dir:str/0/str · returned HumanOutputFormat · level recorded 2026-09-25 a9fed3a61f50d4f0 · report
fixture: signature coordinate:ndarray/2/float · returned ndarray · level recorded 2026-09-26 6ad2196300b77d83 · report
fixture: signature env:MockAtariEnv/0/?, episode_life:bool/0/bool, clip_rewards:bool/0/bool · returned ClipRewardEnv · level recorded 2026-09-26 7bd934aa47da390a · report
0c09148efe18bf06 · report
7e4f579c2aabd9b5 · report
0173e4280d9a9884 · report
fixture: signature listoflists:list/1/list · returned list · level recorded 2026-09-22 8bb63d18cbda13c3 · report
fixture: signature discriminator:MockDiscriminator/0/?, obs:ndarray/2/float, acs:ndarray/2/float, seq_length:int/0/int · returned tuple · level recorded 2026-09-26 7d3ce86ca78ceba8 · report
fixture: signature args:Args/0/? · returned str · level recorded 2026-09-26 ae6c5ba444e45a52 · report
fixture: signature trajs:list/1/ndarray, traj_lens:list/1/int, num_ob:int/0/int · returned tuple · level recorded 2026-09-26 cb3f4da86ee1b680 · report
fixture: returned ActorCritic · level recorded 2026-09-22 86a2d590f55ea39d · report
fixture: returned Discriminator · level recorded 2026-09-22 be4ed3c2e906962c · report
fixture: returned QuarterSizeSigmoid · level recorded 2026-09-22 654066a3d6f0d55b · report
c30fb27c55c474d2 · report
fixture: signature demo_obs:EagerTensor/2/float, demo_act:EagerTensor/1/int, agent_obs:EagerTensor/2/float, agent_act:EagerTensor/1/int · returned tuple · level recorded 2026-09-22 40b17d8ecf42cfe6 · report
93ab130e938732f0 · report
fixture: returned ResNetAIRLDisc · level recorded 2026-09-22 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
7 sibling assemblies for Generative Adversarial Imitation Learning (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 7 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- adversarial_imitation_update entry · level 0 · unverified ·
75e9f2f5049574cb - GAILDiscriminator helper · level 1 · ran ·
58c499108eff7753 - SoftActor helper · level 1 · ran ·
d0f9a51097534c31 - _mix_vars helper · level 1 · ran · violated contract ·
df69a6d635ac78ad - make_gail_input data_transform · level 0 · unverified ·
6782b3c2166c0b4f - _create_fcnn helper · level 1 · ran · our draft was wrong ·
ee98cbfd5f8b7c6d - _join_state_action helper · level 1 · ran · honoured contract ·
e374e2ee3dbb3f45
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- Discriminator entry · level 0 · unverified ·
40b17d8ecf42cfe6
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 7 siblings
- ResNetAIRLDisc entry · level 1 · ran ·
93ab130e938732f0
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 7 siblings
- GAIL entry · level 0 · unverified ·
654066a3d6f0d55b - ActorCritic model · level 1 · ran ·
cb3f4da86ee1b680 - Discriminator model · level 1 · ran ·
86a2d590f55ea39d - QuarterSizeSigmoid helper · level 1 · ran ·
be4ed3c2e906962c
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- iq_loss entry · level 1 · ran · our draft was wrong ·
cf7c0b7b5de1e98b
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- Discriminator entry · level 1 · ran ·
c30fb27c55c474d2
harvested Assembly for Generative Adversarial Imitation Learning (graph method: Generative Adversarial Imitation Learning). 5 bricks; individually on a fixture: 0 ran · 5 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- SamplingPolicyOptimizer entry · level 0 · unverified ·
4117e20071c70a04 - compute_advantage helper · level 0 · unverified ·
12a65e5d7d9e912d - RaggedArray helper · level 0 · unverified ·
0654ba2a385cf2c4 - compute_qvals helper · level 0 · unverified ·
5ce9c8b1227054f5 - raggedstack helper · level 0 · unverified ·
343ea6d8bbc7b6dc
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="1606.03476") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Introduced by this paper: GAIL
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