{"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/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","arxiv_id":"1606.03476","date":"2016-06-10","proceeding":"NeurIPS 2016 12","authors":["Jonathan Ho","Stefano Ermon"],"abstract":"Consider learning a policy from example expert behavior, without interaction\nwith the expert or access to reinforcement signal. One approach is to recover\nthe expert's cost function with inverse reinforcement learning, then extract a\npolicy from that cost function with reinforcement learning. This approach is\nindirect and can be slow. We propose a new general framework for directly\nextracting a policy from data, as if it were obtained by reinforcement learning\nfollowing inverse reinforcement learning. We show that a certain instantiation\nof our framework draws an analogy between imitation learning and generative\nadversarial networks, from which we derive a model-free imitation learning\nalgorithm that obtains significant performance gains over existing model-free\nmethods in imitating complex behaviors in large, high-dimensional environments.","url_abs":"http://arxiv.org/abs/1606.03476v1","url_pdf":"http://arxiv.org/pdf/1606.03476v1.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":"generative-adversarial-imitation-learning","repo_url":"https://github.com/170928/-Review-Generative-Adversarial-Imitation-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/Div99/IQ-Learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/HumanCompatibleAI/deep-rlsp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/KAIST-AILab/deeprl_practice_colab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","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":"generative-adversarial-imitation-learning","repo_url":"https://github.com/Khrylx/PyTorch-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/KshamaDw/collaborative-competitive-games","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/Techget/gail-tf-sc2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/bukysun/gail-traj-eb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/emunaran/stochastic-human-driving-policies-drl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/morikatron/GAIL_PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/nav74neet/gail-tf-gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/ran-weii/cleanil","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/rohitrango/Reward-bias-in-GAIL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/sisl/ngsim_env","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/twni2016/f-IRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/hill-a/stable-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"generative-adversarial-imitation-learning","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/gail_irl_model.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation 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":"ail","method_name":"GAIL"}],"datasets_introduced":[],"methods_introduced":[{"slug":"ail","name":"GAIL","full_name":"Generative Adversarial Imitation Learning"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.03476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03476"}},"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/hill-a/stable-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HumanCompatibleAI/deep-rlsp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Div99/IQ-Learn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Khrylx/PyTorch-RL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Techget/gail-tf-sc2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KAIST-AILab/deeprl_practice_colab","reach":null},{"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/rohitrango/Reward-bias-in-GAIL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/twni2016/f-IRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/170928/-Review-Generative-Adversarial-Imitation-Learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bukysun/gail-traj-eb","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ran-weii/cleanil","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/emunaran/stochastic-human-driving-policies-drl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sisl/ngsim_env","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/morikatron/GAIL_PPO","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KshamaDw/collaborative-competitive-games","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nav74neet/gail-tf-gym","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/gail_irl_model.py","reach":null}],"summary":{"ran":7,"ran_draft_wrong":2,"ran_honours":2,"ran_violates":1,"unverified":24},"by_repo_kind":{"listed":{"samples":36,"ran":12,"repositories":9}},"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":11,"samples":[{"code_sha256_prefix":"cb3f4da86ee1b680","entry":"ActorCritic","repo":"emunaran/stochastic-human-driving-policies-drl","repo_kind":"listed","path":"model/algorithm/gail.py","file_url":"https://github.com/emunaran/stochastic-human-driving-policies-drl/blob/HEAD/model/algorithm/gail.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb3f4da86ee1b680"}},{"code_sha256_prefix":"86a2d590f55ea39d","entry":"Discriminator","repo":"emunaran/stochastic-human-driving-policies-drl","repo_kind":"listed","path":"model/algorithm/gail.py","file_url":"https://github.com/emunaran/stochastic-human-driving-policies-drl/blob/HEAD/model/algorithm/gail.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"86a2d590f55ea39d"}},{"code_sha256_prefix":"c30fb27c55c474d2","entry":"Discriminator","repo":"morikatron/GAIL_PPO","repo_kind":"listed","path":"algo/discriminator.py","file_url":"https://github.com/morikatron/GAIL_PPO/blob/HEAD/algo/discriminator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c30fb27c55c474d2"}},{"code_sha256_prefix":"58c499108eff7753","entry":"GAILDiscriminator","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58c499108eff7753"}},{"code_sha256_prefix":"be4ed3c2e906962c","entry":"QuarterSizeSigmoid","repo":"emunaran/stochastic-human-driving-policies-drl","repo_kind":"listed","path":"model/algorithm/gail.py","file_url":"https://github.com/emunaran/stochastic-human-driving-policies-drl/blob/HEAD/model/algorithm/gail.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be4ed3c2e906962c"}},{"code_sha256_prefix":"93ab130e938732f0","entry":"ResNetAIRLDisc","repo":"twni2016/f-IRL","repo_kind":"listed","path":"firl/models/discrim.py","file_url":"https://github.com/twni2016/f-IRL/blob/HEAD/firl/models/discrim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93ab130e938732f0"}},{"code_sha256_prefix":"d0f9a51097534c31","entry":"SoftActor","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0f9a51097534c31"}},{"code_sha256_prefix":"ee98cbfd5f8b7c6d","entry":"_create_fcnn","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee98cbfd5f8b7c6d"}},{"code_sha256_prefix":"e374e2ee3dbb3f45","entry":"_join_state_action","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e374e2ee3dbb3f45"}},{"code_sha256_prefix":"df69a6d635ac78ad","entry":"_mix_vars","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df69a6d635ac78ad"}},{"code_sha256_prefix":"0173e4280d9a9884","entry":"flatten_lists","repo":"bukysun/gail-traj-eb","repo_kind":"listed","path":"gailtf/algo/trpo_mpi.py","file_url":"https://github.com/bukysun/gail-traj-eb/blob/HEAD/gailtf/algo/trpo_mpi.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"code_sha256_prefix":"cf7c0b7b5de1e98b","entry":"iq_loss","repo":"Div99/IQ-Learn","repo_kind":"listed","path":"iq_learn/iq.py","file_url":"https://github.com/Div99/IQ-Learn/blob/HEAD/iq_learn/iq.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cf7c0b7b5de1e98b"}},{"code_sha256_prefix":"40b17d8ecf42cfe6","entry":"Discriminator","repo":"nav74neet/gail-tf-gym","repo_kind":"listed","path":"gail-ppo-tf-gym/network_models/discriminator.py","file_url":"https://github.com/nav74neet/gail-tf-gym/blob/HEAD/gail-ppo-tf-gym/network_models/discriminator.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":"40b17d8ecf42cfe6"}},{"code_sha256_prefix":"654066a3d6f0d55b","entry":"GAIL","repo":"emunaran/stochastic-human-driving-policies-drl","repo_kind":"listed","path":"model/algorithm/gail.py","file_url":"https://github.com/emunaran/stochastic-human-driving-policies-drl/blob/HEAD/model/algorithm/gail.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":"654066a3d6f0d55b"}},{"code_sha256_prefix":"0654ba2a385cf2c4","entry":"RaggedArray","repo":"KAIST-AILab/deeprl_practice_colab","repo_kind":"listed","path":"day3/gail/policyopt/rl.py","file_url":"https://github.com/KAIST-AILab/deeprl_practice_colab/blob/HEAD/day3/gail/policyopt/rl.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":"0654ba2a385cf2c4"}},{"code_sha256_prefix":"4117e20071c70a04","entry":"SamplingPolicyOptimizer","repo":"KAIST-AILab/deeprl_practice_colab","repo_kind":"listed","path":"day3/gail/policyopt/rl.py","file_url":"https://github.com/KAIST-AILab/deeprl_practice_colab/blob/HEAD/day3/gail/policyopt/rl.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":"4117e20071c70a04"}},{"code_sha256_prefix":"75e9f2f5049574cb","entry":"adversarial_imitation_update","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.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":"75e9f2f5049574cb"}},{"code_sha256_prefix":"12a65e5d7d9e912d","entry":"compute_advantage","repo":"KAIST-AILab/deeprl_practice_colab","repo_kind":"listed","path":"day3/gail/policyopt/rl.py","file_url":"https://github.com/KAIST-AILab/deeprl_practice_colab/blob/HEAD/day3/gail/policyopt/rl.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":"12a65e5d7d9e912d"}},{"code_sha256_prefix":"5ce9c8b1227054f5","entry":"compute_qvals","repo":"KAIST-AILab/deeprl_practice_colab","repo_kind":"listed","path":"day3/gail/policyopt/rl.py","file_url":"https://github.com/KAIST-AILab/deeprl_practice_colab/blob/HEAD/day3/gail/policyopt/rl.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":"5ce9c8b1227054f5"}},{"code_sha256_prefix":"71bdb8bae1ed81f7","entry":"find_task_for_env_id_in_any_benchmark","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/bench/benchmarks.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/benchmarks.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":"71bdb8bae1ed81f7"}},{"code_sha256_prefix":"c45e54fc5355bc2d","entry":"flatten_param","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/algo/trpo_mpi.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/algo/trpo_mpi.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":"c45e54fc5355bc2d"}},{"code_sha256_prefix":"7bd934aa47da390a","entry":"get_benchmark","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/bench/benchmarks.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/benchmarks.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":"7bd934aa47da390a"}},{"code_sha256_prefix":"8bb63d18cbda13c3","entry":"get_cur_ep_rewards","repo":"bukysun/gail-traj-eb","repo_kind":"listed","path":"gailtf/algo/trpo_traj_mpi.py","file_url":"https://github.com/bukysun/gail-traj-eb/blob/HEAD/gailtf/algo/trpo_traj_mpi.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":"8bb63d18cbda13c3"}},{"code_sha256_prefix":"af3d493bdc17ad51","entry":"get_monitor_files","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/bench/monitor.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/monitor.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":"af3d493bdc17ad51"}},{"code_sha256_prefix":"3e82b9de30b1625f","entry":"get_task","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/bench/benchmarks.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/benchmarks.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":"3e82b9de30b1625f"}},{"code_sha256_prefix":"7d3ce86ca78ceba8","entry":"get_task_name","repo":"bukysun/gail-traj-eb","repo_kind":"listed","path":"main_traj_eb.py","file_url":"https://github.com/bukysun/gail-traj-eb/blob/HEAD/main_traj_eb.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":"7d3ce86ca78ceba8"}},{"code_sha256_prefix":"0c09148efe18bf06","entry":"load_results","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/bench/monitor.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/monitor.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":"0c09148efe18bf06"}},{"code_sha256_prefix":"2e4f14f2d4a888ff","entry":"logit_bernoulli_entropy","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/common/tf_util.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/common/tf_util.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":"2e4f14f2d4a888ff"}},{"code_sha256_prefix":"3032d5dbb694f8ba","entry":"logsigmoid","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/common/tf_util.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/common/tf_util.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":"3032d5dbb694f8ba"}},{"code_sha256_prefix":"6782b3c2166c0b4f","entry":"make_gail_input","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/training.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":"6782b3c2166c0b4f"}},{"code_sha256_prefix":"071e746ec3f03d74","entry":"make_output_format","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/logger.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/logger.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":"071e746ec3f03d74"}},{"code_sha256_prefix":"a9fed3a61f50d4f0","entry":"process_coordinates_param_nn_output","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/algo/trpo_mpi.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/algo/trpo_mpi.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":"a9fed3a61f50d4f0"}},{"code_sha256_prefix":"343ea6d8bbc7b6dc","entry":"raggedstack","repo":"KAIST-AILab/deeprl_practice_colab","repo_kind":"listed","path":"day3/gail/policyopt/rl.py","file_url":"https://github.com/KAIST-AILab/deeprl_practice_colab/blob/HEAD/day3/gail/policyopt/rl.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":"343ea6d8bbc7b6dc"}},{"code_sha256_prefix":"ae6c5ba444e45a52","entry":"traj2trans","repo":"bukysun/gail-traj-eb","repo_kind":"listed","path":"gailtf/algo/trpo_traj_mpi.py","file_url":"https://github.com/bukysun/gail-traj-eb/blob/HEAD/gailtf/algo/trpo_traj_mpi.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":"ae6c5ba444e45a52"}},{"code_sha256_prefix":"6ad2196300b77d83","entry":"wrap_deepmind","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/common/atari_wrappers.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/common/atari_wrappers.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":"6ad2196300b77d83"}},{"code_sha256_prefix":"7e4f579c2aabd9b5","entry":"wrap_dqn","repo":"Techget/gail-tf-sc2","repo_kind":"listed","path":"gailtf/baselines/common/atari_wrappers_deprecated.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/common/atari_wrappers_deprecated.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":"7e4f579c2aabd9b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}