{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000167752,0.00005150459,0.00003813567,0.00001222153,0.001186485,0.001166134,0.001925212,0.00001841626,0.000009146883],"category_scores_gemma":[0.0001923645,0.00002995117,0.00002859321,0.00002088642,0.00008266725,0.0002116392,0.0003495716,0.0001062275,0.0001767067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000868247,"about_ca_system_score_gemma":0.00001906291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001097338,"about_ca_topic_score_gemma":0.000005212677,"domain_scores_codex":[0.9994591,0.00001650614,0.00007638545,0.0001143495,0.0001672662,0.0001663662],"domain_scores_gemma":[0.9985939,0.00009728855,0.00005036699,0.001191545,0.00003160837,0.00003524238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[6.5278e-7,0.000002478694,0.000277192,0.000002293115,0.00000679328,0.000003349486,0.0001084994,0.06727173,0.00005034822,0.8937619,0.00117932,0.03733539],"study_design_scores_gemma":[0.0001758966,0.00004970566,0.01018661,0.00001114816,0.000002736119,0.00001534647,0.00001655098,0.8550664,0.0003721338,0.01743314,0.1165144,0.0001559295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002532652,0.0000143036,0.93272,0.008261321,0.0003982317,0.00005038731,2.852388e-8,0.00008044368,0.058222],"genre_scores_gemma":[0.930691,0.00001430557,0.04795191,0.0003655719,0.00008126167,0.000004686381,1.752725e-7,0.000004130965,0.02088695],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9304377,"threshold_uncertainty_score":0.9998708,"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."}}