{"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/discriminator-weighted-offline-imitation-1","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","arxiv_id":"2207.10050","date":"2022-07-20","proceeding":null,"authors":["Haoran Xu","Xianyuan Zhan","Honglei Yin","Huiling Qin"],"abstract":"We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset from suboptimal behaviors. Prior works that address this problem either require that expert data occupies the majority proportion of the offline dataset, or need to learn a reward function and perform offline reinforcement learning (RL) afterwards. In this paper, we aim to address the problem without additional steps of reward learning and offline RL training for the case when demonstrations contain a large proportion of suboptimal data. Built upon behavioral cloning (BC), we introduce an additional discriminator to distinguish expert and non-expert data. We propose a cooperation framework to boost the learning of both tasks, Based on this framework, we design a new IL algorithm, where the outputs of discriminator serve as the weights of the BC loss. Experimental results show that our proposed algorithm achieves higher returns and faster training speed compared to baseline algorithms.","url_abs":"https://arxiv.org/abs/2207.10050v1","url_pdf":"https://arxiv.org/pdf/2207.10050v1.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":"discriminator-weighted-offline-imitation-1","repo_url":"https://github.com/ryanxhr/dwbc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"discriminator-weighted-offline-imitation-1","repo_url":"https://github.com/zexusun/oilca-neurips23","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.10050","atlas_url":"https://app.syntology.ai/?focus=2207.10050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10050"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/ryanxhr/DWBC","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ryanxhr/dwbc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zexusun/oilca-neurips23","reach":null}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"listed":{"samples":13,"ran":6,"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":13,"samples":[{"code_sha256_prefix":"dc45d614f4a18d3a","entry":"Discriminator","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc45d614f4a18d3a"}},{"code_sha256_prefix":"c1b79f00a8278a96","entry":"FullyConnectedNetwork","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c1b79f00a8278a96"}},{"code_sha256_prefix":"0c2b5065cf833c34","entry":"MLP","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c2b5065cf833c34"}},{"code_sha256_prefix":"ecd60efaf01af515","entry":"Normal","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecd60efaf01af515"}},{"code_sha256_prefix":"6a256dc8f875ea5b","entry":"Scalar","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a256dc8f875ea5b"}},{"code_sha256_prefix":"1e5f5f635bdf773a","entry":"extend_and_repeat","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e5f5f635bdf773a"}},{"code_sha256_prefix":"b6455496f9ccd9d2","entry":"Actor","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6455496f9ccd9d2"}},{"code_sha256_prefix":"8cc853990395a427","entry":"DWBC","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8cc853990395a427"}},{"code_sha256_prefix":"28e90238b053734d","entry":"ReparameterizedTanhGaussian","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28e90238b053734d"}},{"code_sha256_prefix":"a7c13f96c95dad29","entry":"TanhGaussianPolicy","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a7c13f96c95dad29"}},{"code_sha256_prefix":"b968e02da3d59339","entry":"iVAE","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b968e02da3d59339"}},{"code_sha256_prefix":"4234aa71c993688f","entry":"vae_args","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4234aa71c993688f"}},{"code_sha256_prefix":"2859ddfc3ce8f887","entry":"weights_init","repo":"zexusun/oilca-neurips23","repo_kind":"listed","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2859ddfc3ce8f887"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}