{"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/bail-best-action-imitation-learning-for-batch-1","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","arxiv_id":"1910.12179","date":"2019-10-27","proceeding":"NeurIPS 2020 12","authors":["Xinyue Chen","Zijian Zhou","Zheng Wang","Che Wang","Yanqiu Wu","Keith Ross"],"abstract":"There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and performance. BAIL learns a V function, uses the V function to select actions it believes to be high-performing, and then uses those actions to train a policy network using imitation learning. For the MuJoCo benchmark, we provide a comprehensive experimental study of BAIL, comparing its performance to four other batch Q-learning and imitation-learning schemes for a large variety of batch datasets. Our experiments show that BAIL's performance is much higher than the other schemes, and is also computationally much faster than the batch Q-learning schemes.","url_abs":"https://arxiv.org/abs/1910.12179v4","url_pdf":"https://arxiv.org/pdf/1910.12179v4.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":"bail-best-action-imitation-learning-for-batch-1","repo_url":"https://github.com/lanyavik/BAIL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.12179","atlas_url":"https://app.syntology.ai/?focus=1910.12179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12179"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lanyavik/BAIL","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"303c000a48de41a3","entry":"L2PenaltyLoss","repo":"lanyavik/BAIL","repo_kind":"official","path":"spinup/spinup/algos/BAIL/bail_training.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/bail_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"303c000a48de41a3"}},{"code_sha256_prefix":"475ab1256cf40ee1","entry":"calc_ue_valiloss","repo":"lanyavik/BAIL","repo_kind":"official","path":"spinup/spinup/algos/BAIL/bail_training.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/bail_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"475ab1256cf40ee1"}},{"code_sha256_prefix":"a8ecbc5e2b2fefaf","entry":"calculate_mc_gain","repo":"lanyavik/BAIL","repo_kind":"official","path":"spinup/spinup/algos/BAIL/main_get_mcret.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/main_get_mcret.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":"a8ecbc5e2b2fefaf"}},{"code_sha256_prefix":"70d424a5dbf32a39","entry":"calculate_mc_return_no_aug","repo":"lanyavik/BAIL","repo_kind":"official","path":"spinup/spinup/algos/BAIL/main_get_mcret.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/main_get_mcret.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":"70d424a5dbf32a39"}},{"code_sha256_prefix":"c74671448905c5d4","entry":"evaluate_policy","repo":"lanyavik/BAIL","repo_kind":"official","path":"spinup/spinup/algos/BAIL/main_static_bail.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/main_static_bail.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c74671448905c5d4"}},{"code_sha256_prefix":"72d5b12cffbf9925","entry":"train_upper_envelope","repo":"lanyavik/BAIL","repo_kind":"official","path":"spinup/spinup/algos/BAIL/bail_training.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/bail_training.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":"72d5b12cffbf9925"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}