{"id":"W2757609746","doi":"10.1609/aaai.v32i1.11775","title":"OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Open Philanthropy Project; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Adversarial system; Generative grammar; Artificial intelligence; Function (biology); Set (abstract data type); Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001556608,0.0007570882,0.0007915881,0.0006981728,0.001089512,0.001105429,0.003395611,0.0005023198,0.0001428128],"category_scores_gemma":[0.00276602,0.0006747153,0.0004524616,0.001083617,0.0007594664,0.0007130604,0.004832258,0.002695606,0.0001894779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006959162,"about_ca_system_score_gemma":0.001137152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002847626,"about_ca_topic_score_gemma":0.000006758771,"domain_scores_codex":[0.9946806,0.0001629085,0.001595943,0.001285649,0.001426065,0.0008488584],"domain_scores_gemma":[0.9942142,0.0001240396,0.002441108,0.0007746177,0.002215725,0.0002302809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004092481,0.00004081823,0.0000592703,0.00009855376,0.00007909249,8.566801e-7,0.003590338,0.7516776,0.009525106,0.2333348,0.00009474572,0.001457806],"study_design_scores_gemma":[0.00006438993,0.0004121511,0.00001878878,0.0009610763,0.0000633462,0.000006433413,0.0007516318,0.8895832,0.08529224,0.02200944,0.0002297254,0.0006075866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02887597,0.00001901591,0.9536433,0.002135431,0.002408326,0.001310169,0.000003135333,0.0003740782,0.01123061],"genre_scores_gemma":[0.9514592,0.0002100435,0.04484699,0.0002010177,0.001063011,0.00006539036,0.000009995584,0.00006125018,0.00208311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9225832,"threshold_uncertainty_score":0.9999315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1387106207647681,"score_gpt":0.3290586757371067,"score_spread":0.1903480549723386,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}