{"id":"W2098152875","doi":"10.1145/1390156.1390199","title":"Reinforcement learning in the presence of rare events","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004049807,0.00008079305,0.000101192,0.00007866624,0.00009570603,0.00001623735,0.001144111,0.00002847652,0.00003573631],"category_scores_gemma":[0.0001572658,0.00005500599,0.00003862513,0.0003967098,0.00003985817,0.0003015091,0.0002377951,0.0001904931,0.00003364893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001951795,"about_ca_system_score_gemma":0.00005030677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005211842,"about_ca_topic_score_gemma":0.000001724068,"domain_scores_codex":[0.9987512,0.0001063937,0.0002761692,0.0001536449,0.0005059528,0.0002065974],"domain_scores_gemma":[0.9991943,0.0001779613,0.0001112557,0.0004477616,0.00004494633,0.00002375884],"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":[0.000001927198,0.00001094089,0.01865274,0.000007413279,0.000003547759,0.000009798431,0.002760735,0.9675706,0.00004298578,0.01015365,0.0003907185,0.000394934],"study_design_scores_gemma":[0.0003669594,0.0001893081,0.02848341,0.00003639524,0.000001612021,0.00002917961,0.000221432,0.9664241,0.0007118171,0.0001238183,0.003281791,0.0001301656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01932122,0.00001884029,0.9548401,0.0003906584,0.00008585793,0.0001869909,1.975995e-8,0.00005512386,0.02510119],"genre_scores_gemma":[0.9886237,0.00003458071,0.006092967,0.0001794256,0.00001063257,0.000008112236,9.291272e-7,0.00000319771,0.005046399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9693025,"threshold_uncertainty_score":0.2243079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02929513975464497,"score_gpt":0.2554733698838317,"score_spread":0.2261782301291868,"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."}}