{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001342222,0.001092856,0.001020749,0.0004259146,0.0002432424,0.0006623615,0.00137859,0.001510787,0.003138666],"category_scores_gemma":[0.004129024,0.0006437295,0.0006564279,0.000319001,0.001377922,0.001323509,0.001687906,0.002153949,0.0005173826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007007261,"about_ca_system_score_gemma":0.001014509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002456617,"about_ca_topic_score_gemma":0.002901818,"domain_scores_codex":[0.9995301,0.0001812573,0.00001775588,0.00009818457,0.0001177753,0.00005499467],"domain_scores_gemma":[0.9987026,0.0009483231,0.00008652006,0.0001089871,0.00008629427,0.00006719374],"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":[0.00007112381,0.0000378144,0.0004983076,0.00004713445,0.00004314975,0.0000779366,0.00003688623,0.9540747,0.0011995,0.01308177,0.001165644,0.02966597],"study_design_scores_gemma":[0.000006698895,0.00001415227,0.00003725935,0.000005296806,0.000002843006,0.00001163116,0.000001915839,0.9931121,0.0002947256,0.006295424,0.0002133906,0.000004569984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0155947,0.0002482997,0.9807891,0.0002513656,0.00004164995,0.00005621738,0.0000731185,0.000866705,0.002078901],"genre_scores_gemma":[0.8252488,0.0002359529,0.1679942,0.0004770062,0.00005470574,0.0003227045,0.000319712,0.0002323251,0.005114532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003138666,"threshold_uncertainty_score":0.01049989,"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."}}