{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/ail","slug":"ail","name":"GAIL","full_name":"Generative Adversarial Imitation Learning","full_name_withheld":false,"description_markdown":"**Generative Adversarial Imitation Learning** presents a new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Generative Adversarial Imitation Learning","paper":"/paper/generative-adversarial-imitation-learning","first_author":"Jonathan Ho","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/generative-adversarial-imitation-learning"},"source":{"url":"http://arxiv.org/abs/1606.03476v1","title":"Generative Adversarial Imitation Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Adversarial Training","url":"/methods/category/adversarial-training","pwc_aliases":[]}],"n_papers_tagged":41,"archive_num_papers":41,"papers_newest_first":[{"paper":null,"slug":"imitation-learning-of-correlated-policies-in","title":"Imitation Learning of Correlated Policies in Stackelberg Games","date":"2025-03-11","arxiv_id":"2503.08883","n_code_links":0,"syntology":null},{"paper":null,"slug":"quality-diversity-imitation-learning","title":"Quality Diversity Imitation Learning","date":"2024-10-08","arxiv_id":"2410.06151","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-spectrum-efficiency-in-6g-satellite","title":"Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning","date":"2024-09-27","arxiv_id":"2409.18718","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-03200","title":"Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors","date":"2024-08-06","arxiv_id":"2408.03200","n_code_links":0,"syntology":null},{"paper":null,"slug":"racil-ray-tracing-based-multi-uav-obstacle","title":"RaCIL: Ray Tracing based Multi-UAV Obstacle Avoidance through Composite Imitation Learning","date":"2024-06-24","arxiv_id":"2407.02520","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-reward-adversarial-imitation","title":"Diffusion-Reward Adversarial Imitation Learning","date":"2024-05-25","arxiv_id":"2405.16194","n_code_links":0,"syntology":null},{"paper":null,"slug":"c-gail-stabilizing-generative-adversarial","title":"C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory","date":"2024-02-26","arxiv_id":"2402.16349","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-gradient-explosion-in-generative","title":"Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective","date":"2023-12-18","arxiv_id":"2312.11214","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-generative-adversarial-imitation","slug":"hierarchical-generative-adversarial-imitation","title":"Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments","date":"2023-02-09","arxiv_id":"2302.04823","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gustavokcouto/hgail"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"latent-policies-for-adversarial-imitation","title":"Latent Policies for Adversarial Imitation Learning","date":"2022-06-22","arxiv_id":"2206.11299","n_code_links":0,"syntology":null},{"paper":null,"slug":"diverse-imitation-learning-via-self-1","title":"Diverse Imitation Learning via Self-Organizing Generative Models","date":"2022-05-06","arxiv_id":"2205.03484","n_code_links":0,"syntology":null},{"paper":"/paper/gail-pt-a-generic-intelligent-penetration","slug":"gail-pt-a-generic-intelligent-penetration","title":"GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning","date":"2022-04-05","arxiv_id":"2204.01975","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-valuedice-does-it-really-improve","title":"Rethinking ValueDice: Does It Really Improve Performance?","date":"2022-02-05","arxiv_id":"2202.02468","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-valuedice-does-it-really-improve-1","title":"Rethinking ValueDice: Does It Really Improve Performance?","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/continuous-control-with-action-quantization-1","slug":"continuous-control-with-action-quantization-1","title":"Continuous Control with Action Quantization from Demonstrations","date":"2021-10-19","arxiv_id":"2110.10149","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-adversarial-imitation-learning-for-1","title":"Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments","date":"2021-10-16","arxiv_id":"2110.08586","n_code_links":0,"syntology":null},{"paper":null,"slug":"diverse-imitation-learning-via-self","title":"Diverse Imitation Learning via Self-OrganizingGenerative Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"stabilized-likelihood-based-imitation","title":"Stabilized Likelihood-based Imitation Learning via Denoising Continuous Normalizing Flow","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-efficient-generative-adversarial","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","date":"2021-08-19","arxiv_id":"2108.08765","n_code_links":0,"syntology":null},{"paper":"/paper/a-pragmatic-look-at-deep-imitation-learning","slug":"a-pragmatic-look-at-deep-imitation-learning","title":"A Pragmatic Look at Deep Imitation Learning","date":"2021-08-04","arxiv_id":"2108.01867","n_code_links":1,"syntology":null},{"paper":null,"slug":"imitation-by-predicting-observations","title":"Imitation by Predicting Observations","date":"2021-07-08","arxiv_id":"2107.03851","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-generative-adversarial-imitation","title":"On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning","date":"2021-06-30","arxiv_id":"2107.00116","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-adversarial-imitation-learning-for","title":"Generative Adversarial Imitation Learning for Empathy-based AI","date":"2021-05-27","arxiv_id":"2105.13328","n_code_links":0,"syntology":null},{"paper":null,"slug":"gan-based-interactive-reinforcement-learning","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","date":"2021-04-14","arxiv_id":"2104.06600","n_code_links":0,"syntology":null},{"paper":null,"slug":"online-apprenticeship-learning","title":"Online Apprenticeship Learning","date":"2021-02-13","arxiv_id":"2102.06924","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-imitation-with-reinforcement-learning","title":"Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-is-the-reward-for-handwriting","title":"What is the Reward for Handwriting? -- Handwriting Generation by Imitation Learning","date":"2020-09-23","arxiv_id":"2009.10962","n_code_links":0,"syntology":null},{"paper":"/paper/addressing-reward-bias-in-adversarial","slug":"addressing-reward-bias-in-adversarial","title":"Addressing reward bias in Adversarial Imitation Learning with neutral reward functions","date":"2020-09-20","arxiv_id":"2009.09467","n_code_links":1,"syntology":null},{"paper":"/paper/non-adversarial-imitation-learning-and-its","slug":"non-adversarial-imitation-learning-and-its","title":"Non-Adversarial Imitation Learning and its Connections to Adversarial Methods","date":"2020-08-08","arxiv_id":"2008.03525","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OlegArenz/O-NAIL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"concurrent-training-improves-the-performance","title":"Concurrent Training Improves the Performance of Behavioral Cloning from Observation","date":"2020-08-03","arxiv_id":"2008.01205","n_code_links":0,"syntology":null},{"paper":null,"slug":"lagrangian-duality-in-reinforcement-learning","title":"Lagrangian Duality in Reinforcement Learning","date":"2020-07-20","arxiv_id":"2007.09998","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-will-generative-adversarial-imitation","title":"When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence","date":"2020-06-24","arxiv_id":"2006.13506","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-soft-advantage-fitting-imitation","slug":"adversarial-soft-advantage-fitting-imitation","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","date":"2020-06-23","arxiv_id":"2006.13258","n_code_links":3,"syntology":null},{"paper":null,"slug":"modeling-human-driving-behavior-through","title":"Modeling Human Driving Behavior through Generative Adversarial Imitation Learning","date":"2020-06-10","arxiv_id":"2006.06412","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-infidelity-learning-for-model","slug":"adversarial-infidelity-learning-for-model","title":"Adversarial Infidelity Learning for Model Interpretation","date":"2020-06-09","arxiv_id":"2006.05379","n_code_links":1,"syntology":null},{"paper":"/paper/wasserstein-distance-guided-adversarial","slug":"wasserstein-distance-guided-adversarial","title":"Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration","date":"2020-06-05","arxiv_id":"2006.03503","n_code_links":1,"syntology":null},{"paper":null,"slug":"triple-gail-a-multi-modal-imitation-learning","title":"Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets","date":"2020-05-19","arxiv_id":"2005.10622","n_code_links":0,"syntology":null},{"paper":"/paper/off-policy-adversarial-inverse-reinforcement","slug":"off-policy-adversarial-inverse-reinforcement","title":"Off-Policy Adversarial Inverse Reinforcement Learning","date":"2020-05-03","arxiv_id":"2005.01138","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-adversarial-imitation-learning-2","title":"Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate","date":"2020-03-08","arxiv_id":"2003.03709","n_code_links":0,"syntology":null},{"paper":null,"slug":"support-weighted-adversarial-imitation","title":"Support-weighted Adversarial Imitation Learning","date":"2020-02-20","arxiv_id":"2002.08803","n_code_links":0,"syntology":null},{"paper":"/paper/generative-adversarial-imitation-learning","slug":"generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","arxiv_id":"1606.03476","n_code_links":18,"syntology":{"ran":24,"of":36,"n_ran_checked":22,"n_instrument":2,"unverified":12,"pointer_only":15,"phrase":"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","official":null}}],"papers_shown":41,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":41,"with_a_code_link":11,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":41,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/ail/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/ail/papers/ran/1","json":"/method/ail/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/imitation-learning","name":"Imitation Learning","papers":37},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":13},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":8},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":8},{"task":"/task/mujoco","name":"MuJoCo","papers":6},{"task":"/task/continuous-control","name":"Continuous Control","papers":5},{"task":"/task/continuous-control","name":"continuous-control","papers":5},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":2},{"task":"/task/autonomous-navigation","name":"Autonomous Navigation","papers":2},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/behavioural-cloning","name":"Behavioural cloning","papers":1},{"task":"/task/collision-avoidance","name":"Collision Avoidance","papers":1},{"task":"/task/d4rl","name":"D4RL","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/disentanglement","name":"Disentanglement","papers":1}],"tasks_shown":20,"n_tasks":34,"usage_by_year":[{"year":"2016","papers":1},{"year":"2020","papers":14},{"year":"2021","papers":12},{"year":"2022","papers":5},{"year":"2023","papers":2},{"year":"2024","papers":6},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ail"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=GAIL","read_at":"2026-10-05T00:51:47+00:00","query":"GAIL","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1606.03476","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'GAIL' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Option-GAIL","Triple-GAIL"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"29e73bdeacba14c0a5941b498b70de487c1dddf1e9e7d2beee9a03fb996c8160","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}