{"id":"W6987579751","doi":"","title":"Temporal credit assignment via traces in reinforcement learning","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Function (biology); Q-learning; Reinforcement; Bellman equation; Temporal difference learning; Variance (accounting); Value (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001945424,0.0008423979,0.0008606276,0.0004520167,0.0004576315,0.001251264,0.001179411,0.001223008,0.003720446],"category_scores_gemma":[0.01173317,0.0003311425,0.0005505972,0.0005490355,0.001903668,0.002165637,0.001367993,0.002498121,0.0003591065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001439961,"about_ca_system_score_gemma":0.001411722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003354074,"about_ca_topic_score_gemma":0.002432211,"domain_scores_codex":[0.9990326,0.000435207,0.0000490522,0.0001923294,0.0002012372,0.00008956892],"domain_scores_gemma":[0.9958627,0.00301935,0.0003049499,0.0002578606,0.000326684,0.0002284052],"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":[0.0001237852,0.000122659,0.001078179,0.0001081459,0.00004635884,0.0001116642,0.0001727515,0.7067978,0.001501668,0.2215052,0.001651591,0.06678014],"study_design_scores_gemma":[0.00001867664,0.00004447556,0.0000866346,0.00001303301,0.000006819774,0.00001306012,0.00001013255,0.9137071,0.0004551568,0.08476455,0.0008714151,0.000008813398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01562293,0.0003220763,0.9797776,0.0004955929,0.00006736591,0.00004643743,0.00003855151,0.0002527524,0.00337667],"genre_scores_gemma":[0.8505973,0.000702234,0.1410335,0.0002225127,0.00008917419,0.0002254592,0.0001001935,0.00009849518,0.006931284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003720446,"threshold_uncertainty_score":0.01244611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01857803569777591,"score_gpt":0.2430754551619413,"score_spread":0.2244974194641654,"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."}}