{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001473986,0.001168755,0.001065721,0.0004470699,0.0002592816,0.0007716866,0.0014935,0.001711967,0.003541623],"category_scores_gemma":[0.004755085,0.0006989657,0.0007184935,0.0003417478,0.001424044,0.001501595,0.001879192,0.002408573,0.0005879542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007720591,"about_ca_system_score_gemma":0.001067672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002520568,"about_ca_topic_score_gemma":0.002930377,"domain_scores_codex":[0.9994658,0.0002135376,0.00001934878,0.0001142205,0.0001268661,0.00006031358],"domain_scores_gemma":[0.9985569,0.001052653,0.00009522172,0.000128706,0.00009127895,0.00007519322],"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":[0.00007669878,0.00003919195,0.000522191,0.00004919881,0.00004594789,0.00008145621,0.00003961651,0.95446,0.001078618,0.01461446,0.001296569,0.02769596],"study_design_scores_gemma":[0.00000723207,0.00001327952,0.00003632899,0.000005370765,0.000002749299,0.00001142191,0.000001933193,0.9921956,0.0002621671,0.007242703,0.0002166945,0.000004554428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01630244,0.0002760922,0.9794881,0.0003088435,0.00004748171,0.00006520789,0.00009329027,0.0009759432,0.002442667],"genre_scores_gemma":[0.8183374,0.0002460204,0.1740828,0.0005337909,0.00006389813,0.0003595386,0.0003693627,0.0002755499,0.005731655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003541623,"threshold_uncertainty_score":0.01184791,"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."}}