{"id":"W2962845991","doi":"10.1609/aaai.v32i1.11775","title":"OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"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; Artificial intelligence; Generative grammar; Machine learning; Function (biology); Set (abstract data type)","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0008141189,0.000343009,0.000307431,0.0005275657,0.001378146,0.0004948287,0.0006989074,0.00015597,0.0003572257],"category_scores_gemma":[0.0007218023,0.0003412949,0.0001582899,0.001018073,0.0002441881,0.001284854,0.0008994888,0.0006754344,0.0006592838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005493599,"about_ca_system_score_gemma":0.0004604634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003270934,"about_ca_topic_score_gemma":0.00001223917,"domain_scores_codex":[0.9969503,0.0003270291,0.0006446605,0.0006397456,0.0007003957,0.0007379299],"domain_scores_gemma":[0.9982073,0.00008673546,0.000393315,0.0006221466,0.0004438845,0.000246662],"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":[0.000008478677,0.00001153882,0.0001854283,0.000007018304,0.00005080866,0.000005745603,0.002387827,0.9361864,0.004465089,0.05573429,0.0004011025,0.0005563085],"study_design_scores_gemma":[0.0006708681,0.0005014227,0.00008517036,0.00004082955,0.00001966262,0.00002290283,0.0003804266,0.9817604,0.003736579,0.0001651416,0.01220576,0.000410766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005584269,0.000008727493,0.968722,0.0006079281,0.0008374642,0.0003038921,1.545662e-7,0.0006015084,0.02333404],"genre_scores_gemma":[0.6187307,0.00004575967,0.3572925,0.0007252691,0.001826092,0.00001730259,0.0000178376,0.00004470958,0.02129986],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6131464,"threshold_uncertainty_score":0.9999219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0495135636832109,"score_gpt":0.2943951343330231,"score_spread":0.2448815706498121,"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."}}