{"id":"W2523728418","doi":"10.1609/aaai.v31i1.10916","title":"The Option-Critic Architecture","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":209,"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; Architecture; Abstraction; Key (lock); Artificial intelligence; Economics; Computer security; 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":[0.0009809321,0.0008233829,0.0006473402,0.0003459276,0.0004679998,0.001291565,0.001527719,0.001421225,0.004629966],"category_scores_gemma":[0.004000276,0.0006060058,0.0006058979,0.0003526702,0.001697263,0.002424369,0.001848369,0.003288094,0.0009195589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009343338,"about_ca_system_score_gemma":0.001417995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002643663,"about_ca_topic_score_gemma":0.003257169,"domain_scores_codex":[0.9994487,0.000161813,0.0000298946,0.0001448315,0.0001618101,0.0000529112],"domain_scores_gemma":[0.9990978,0.0004315622,0.00007432087,0.0001556578,0.0001434311,0.00009728146],"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":[0.00008746639,0.00003673113,0.0006332994,0.0001013999,0.00006939502,0.0001662118,0.0001141666,0.5939296,0.003040292,0.3473042,0.003045764,0.05147145],"study_design_scores_gemma":[0.0000179705,0.00002198842,0.00009102263,0.00001684622,0.00001431791,0.0000402838,0.000005984923,0.8564832,0.0005388039,0.140002,0.002754554,0.0000130512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01001272,0.0004054291,0.9754112,0.001000065,0.00009678536,0.00004522463,0.00008872127,0.0005385211,0.01240119],"genre_scores_gemma":[0.7117746,0.0007622546,0.2723404,0.0004591023,0.0001331146,0.0002833849,0.0001809902,0.0001588672,0.0139074],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004629966,"threshold_uncertainty_score":0.0154888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08507794004948784,"score_gpt":0.3192055271439572,"score_spread":0.2341275870944694,"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."}}