{"id":"W2794940174","doi":"10.1609/aimag.v39i1.2780","title":"Constructing Temporal Abstractions Autonomously in Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"AI Magazine","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"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; Computer science; Abstraction; Artificial intelligence; Thread (computing); Architecture; Programming language","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":[0.001183973,0.0005161537,0.000495887,0.000211594,0.000397307,0.0008488545,0.001061952,0.0008354679,0.001459675],"category_scores_gemma":[0.003628657,0.0004635208,0.0004786377,0.0002410824,0.001734301,0.002194992,0.001460179,0.0019125,0.0002134984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007162316,"about_ca_system_score_gemma":0.0009209386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001988796,"about_ca_topic_score_gemma":0.002458296,"domain_scores_codex":[0.9995729,0.0001662266,0.00002012528,0.00009345554,0.0000941359,0.00005311233],"domain_scores_gemma":[0.9989016,0.0006443942,0.0001234772,0.0001455816,0.00008865081,0.00009634471],"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":[0.0001642791,0.0000647896,0.0009768545,0.00008972039,0.00006265267,0.0001743375,0.0003130243,0.7613071,0.005656652,0.1849303,0.0009968576,0.04526341],"study_design_scores_gemma":[0.0000180777,0.00002681528,0.00005950228,0.000007279524,0.000008949527,0.00001496523,0.00001122308,0.9364632,0.000899284,0.06173326,0.0007495049,0.00000795724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03014789,0.0001681402,0.9665736,0.0003014618,0.00003270841,0.00002725927,0.0000255684,0.0003922803,0.002331095],"genre_scores_gemma":[0.8272767,0.000243767,0.1695616,0.0001190817,0.00002579083,0.0001148586,0.00005669069,0.0000677209,0.0025337],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001988796,"threshold_uncertainty_score":0.006261528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01520819445972775,"score_gpt":0.2693107594008761,"score_spread":0.2541025649411484,"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."}}