{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005423796,0.0006053114,0.001335213,0.0005195242,0.000511083,0.001207176,0.00135466,0.001002378,0.0007559364],"category_scores_gemma":[0.02876924,0.0005615408,0.0003370768,0.0003922225,0.002151825,0.001950125,0.001232707,0.001795448,0.0001231783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001464597,"about_ca_system_score_gemma":0.001210561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003905157,"about_ca_topic_score_gemma":0.002809828,"domain_scores_codex":[0.9979353,0.001166419,0.00007876464,0.0003119685,0.0003208163,0.0001867944],"domain_scores_gemma":[0.9752204,0.02060566,0.001762439,0.0009028792,0.00101118,0.0004973779],"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":[0.0001721644,0.00004525064,0.002029529,0.00004850436,0.00005034948,0.0001192144,0.00008374515,0.9518221,0.0006375588,0.02904214,0.0003873829,0.01556202],"study_design_scores_gemma":[0.000022967,0.00001976834,0.000176904,0.000004395627,0.000005495001,0.00001290848,0.000006364387,0.9818651,0.0002179123,0.01754811,0.0001156209,0.000004466467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1702826,0.0003902384,0.8254398,0.0008453847,0.00006240057,0.00005441544,0.00004530167,0.0004234144,0.002456508],"genre_scores_gemma":[0.9593086,0.0001178161,0.03944663,0.0001132392,0.00004079888,0.00006016507,0.00003148433,0.00003313723,0.0008481294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005423796,"threshold_uncertainty_score":0.02868414,"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."}}