{"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/f-gail-learning-f-divergence-for-generative","title":"$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning","arxiv_id":"2010.01207","date":"2020-10-02","proceeding":null,"authors":["Xin Zhang","Yanhua Li","Ziming Zhang","Zhi-Li Zhang"],"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.","url_abs":"https://arxiv.org/abs/2010.01207v2","url_pdf":"https://arxiv.org/pdf/2010.01207v2.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":"f-gail-learning-f-divergence-for-generative","repo_url":"https://github.com/fGAIL3456/fGAIL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.01207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01207"}},"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/fGAIL3456/fGAIL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"2d15f050207aff53","entry":"merge","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/model_utils.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/model_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d15f050207aff53"}},{"code_sha256_prefix":"6aff48ec0d1463e1","entry":"compute_cov_a","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/algo/kfac.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/algo/kfac.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6aff48ec0d1463e1"}},{"code_sha256_prefix":"d9fd61d47e236b09","entry":"compute_cov_g","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/algo/kfac.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/algo/kfac.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9fd61d47e236b09"}},{"code_sha256_prefix":"8a3ac7de797e022f","entry":"power_series_full_jac_exact_trace","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/matrix_utils.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/matrix_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a3ac7de797e022f"}},{"code_sha256_prefix":"ff79b75e8d4e8e73","entry":"power_series_matrix_logarithm_trace","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/matrix_utils.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/matrix_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff79b75e8d4e8e73"}},{"code_sha256_prefix":"3ffb195b7f9d2a6a","entry":"process_maxmin_groupsize","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/model_utils.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ffb195b7f9d2a6a"}},{"code_sha256_prefix":"f31c6c36e11645e2","entry":"split","repo":"fGAIL3456/fGAIL","repo_kind":"official","path":"a2c_ppo_acktr/model_utils.py","file_url":"https://github.com/fGAIL3456/fGAIL/blob/HEAD/a2c_ppo_acktr/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f31c6c36e11645e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}