{"id":"W7132969921","doi":"","title":"Learning the Discount Factor in Inverse Reinforcement Learning with Application to Animal Behaviour","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Foraging; Reinforcement learning; Function (biology); Convexity; Preference; Factor (programming language)","routes":{"ca_aff":true,"ca_fund":false,"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","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001134938,0.0009544466,0.0007098838,0.0007206628,0.001045637,0.0009768135,0.001999424,0.0003983664,0.0001148714],"category_scores_gemma":[0.000423068,0.0007836461,0.0001744826,0.002795148,0.0001157366,0.0005639902,0.0006592689,0.003031911,0.001273436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008244862,"about_ca_system_score_gemma":0.000553313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003004808,"about_ca_topic_score_gemma":0.001503029,"domain_scores_codex":[0.9936885,0.000420933,0.001077423,0.001517386,0.001978987,0.00131682],"domain_scores_gemma":[0.9964411,0.0003971857,0.001233108,0.001219878,0.000386361,0.000322317],"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":[0.0001852586,0.00002762268,0.02345701,0.0001169338,0.00005414333,0.00002554597,0.1090689,0.8639304,0.0007825994,0.0004595721,0.00007129807,0.001820711],"study_design_scores_gemma":[0.0007330782,0.002045787,0.07246872,0.0007269036,0.00009045078,0.000006404081,0.05711802,0.8630376,0.0004684963,0.000003652603,0.002197942,0.001102964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5196345,0.00002560273,0.4739012,0.001111246,0.000588819,0.00274892,6.819658e-7,0.0004007105,0.001588238],"genre_scores_gemma":[0.9300752,0.00009668767,0.001216345,0.0001287909,0.0001495025,0.0005135833,0.0002640594,0.0001648396,0.06739094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4726849,"threshold_uncertainty_score":0.9995042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02195637573274086,"score_gpt":0.317475079676105,"score_spread":0.2955187039433642,"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."}}