{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/sample-efficient-imitation-learning-via","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","arxiv_id":"1809.02064","date":"2018-09-06","proceeding":null,"authors":["Lionel Blondé","Alexandros Kalousis"],"abstract":"GAIL is a recent successful imitation learning architecture that exploits the\nadversarial training procedure introduced in GANs. Albeit successful at\ngenerating behaviours similar to those demonstrated to the agent, GAIL suffers\nfrom a high sample complexity in the number of interactions it has to carry out\nin the environment in order to achieve satisfactory performance. We\ndramatically shrink the amount of interactions with the environment necessary\nto learn well-behaved imitation policies, by up to several orders of magnitude.\nOur framework, operating in the model-free regime, exhibits a significant\nincrease in sample-efficiency over previous methods by simultaneously a)\nlearning a self-tuned adversarially-trained surrogate reward and b) leveraging\nan off-policy actor-critic architecture. We show that our approach is simple to\nimplement and that the learned agents remain remarkably stable, as shown in our\nexperiments that span a variety of continuous control tasks. Video\nvisualisations available at: \\url{https://youtu.be/-nCsqUJnRKU}.","url_abs":"http://arxiv.org/abs/1809.02064v3","url_pdf":"http://arxiv.org/pdf/1809.02064v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sample-efficient-imitation-learning-via","repo_url":"https://github.com/lionelblonde/sam-tf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"sample-efficient-imitation-learning-via","repo_url":"https://github.com/Kaixhin/imitation-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sample-efficient-imitation-learning-via","repo_url":"https://github.com/lionelblonde/sam-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.02064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02064"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kaixhin/imitation-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lionelblonde/sam-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lionelblonde/sam-tf","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"510e3fb9fef298ac","entry":"copy_and_add_seed","repo":"lionelblonde/sam-pytorch","repo_kind":"listed","path":"spawner.py","file_url":"https://github.com/lionelblonde/sam-pytorch/blob/HEAD/spawner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"510e3fb9fef298ac"}},{"code_sha256_prefix":"e2d82e92f611ee99","entry":"rand_tuple_from_list","repo":"lionelblonde/sam-pytorch","repo_kind":"listed","path":"spawner.py","file_url":"https://github.com/lionelblonde/sam-pytorch/blob/HEAD/spawner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2d82e92f611ee99"}},{"code_sha256_prefix":"251cd5181c4a9260","entry":"traj_segment_generator","repo":"lionelblonde/sam-tf","repo_kind":"official","path":"imitation/imitation_algorithms/sam.py","file_url":"https://github.com/lionelblonde/sam-tf/blob/HEAD/imitation/imitation_algorithms/sam.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"251cd5181c4a9260"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}