{"id":"W3215887789","doi":"10.1109/tai.2021.3117743","title":"Delayed Reward Bernoulli Bandits: Optimal Policy and Predictive Meta-Algorithm PARDI","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bernoulli's principle; Computer science; Outcome (game theory); Reinforcement learning; Mathematical optimization; Index (typography); Algorithm; Range (aeronautics); Artificial intelligence; Mathematics; Mathematical economics; Engineering","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001637862,0.0003932847,0.0007200016,0.0006974454,0.0007294998,0.0005293017,0.0006665266,0.0002183167,0.001888558],"category_scores_gemma":[0.0009832603,0.0003227812,0.000463092,0.002664389,0.0006254753,0.0007017735,0.00002035836,0.000774104,0.0008024031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871549,"about_ca_system_score_gemma":0.0004765511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001668212,"about_ca_topic_score_gemma":0.000235653,"domain_scores_codex":[0.9940932,0.0005434546,0.001127018,0.001308426,0.002191459,0.0007364607],"domain_scores_gemma":[0.9946184,0.002598298,0.0001877464,0.0009733269,0.001164422,0.0004578179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000276168,0.0004115898,0.000001623381,0.000004302745,0.0007166246,0.0001603249,0.0009330759,0.2276233,0.0007190156,0.0004685817,0.0002753208,0.7684101],"study_design_scores_gemma":[0.0001828438,0.0009088996,0.00003938625,0.00002525387,0.0005925699,0.0002246008,0.004038605,0.3348873,0.5582369,0.09052975,0.00952305,0.0008108112],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001580155,0.0003324662,0.9934435,0.002303076,0.0007755588,0.0003606928,0.0006889727,0.000102471,0.0004130855],"genre_scores_gemma":[0.9445038,0.0008550307,0.04616744,0.0004452493,0.0005705924,0.0001833241,0.00001484475,0.00007540531,0.007184322],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9472761,"threshold_uncertainty_score":0.9999756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1953330603976514,"score_gpt":0.4366686007048083,"score_spread":0.2413355403071569,"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."}}