{"id":"W2964227312","doi":"10.1609/aaai.v31i1.10916","title":"The Option-Critic Architecture","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":695,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Flexibility (engineering); Computer science; Abstraction; Architecture; Key (lock); Artificial intelligence; Machine learning; Computer security; Economics; Management; Epistemology","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":[0.0009561714,0.0008001137,0.0006322312,0.0003441047,0.0004525835,0.001186317,0.001519565,0.001340026,0.004058838],"category_scores_gemma":[0.003774069,0.000599154,0.0005988979,0.0003453439,0.001724017,0.002400473,0.001797566,0.003212797,0.0008594168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008784215,"about_ca_system_score_gemma":0.001368139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002566592,"about_ca_topic_score_gemma":0.003196265,"domain_scores_codex":[0.9994716,0.0001520029,0.00002953173,0.000135506,0.0001607638,0.00005060763],"domain_scores_gemma":[0.9991235,0.0004165965,0.00007339577,0.0001515151,0.000141286,0.00009372817],"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":[0.00008669641,0.00003656457,0.000623595,0.0001043588,0.00007058808,0.0001705869,0.0001150471,0.5908361,0.003428852,0.346081,0.002975099,0.05547143],"study_design_scores_gemma":[0.00001798063,0.00002321983,0.00009602516,0.00001636447,0.00001488949,0.00004263932,0.000005768986,0.8634123,0.0005979657,0.1329641,0.002794942,0.00001380048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008548323,0.0003637341,0.9795291,0.0008304197,0.0000826785,0.00004068292,0.00007408186,0.0005093313,0.01002167],"genre_scores_gemma":[0.6983116,0.0007582029,0.2875843,0.0004188191,0.000126762,0.0002796353,0.0001630089,0.000146916,0.01221076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004058838,"threshold_uncertainty_score":0.01357818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411873004184306,"score_gpt":0.2683013584491692,"score_spread":0.2541826284073262,"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."}}