{"id":"W3134156689","doi":"10.48550/arxiv.2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Convergence (economics); Lambda; Algorithm; Function (biology); Computer science; Mathematics; Artificial intelligence; Physics; Economics; Quantum mechanics","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"],"consensus_categories":[],"category_scores_codex":[0.0006551612,0.0004994103,0.0005649615,0.0002773488,0.0004744309,0.0006192318,0.002225643,0.0003642071,0.00005043736],"category_scores_gemma":[0.0002974081,0.0006388715,0.0004758276,0.0004847585,0.00006776971,0.0006686194,0.003840535,0.00118505,0.00004059354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004360257,"about_ca_system_score_gemma":0.0003718743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004124794,"about_ca_topic_score_gemma":0.00000266262,"domain_scores_codex":[0.9968472,0.0001930392,0.0004738912,0.001529479,0.0002332164,0.0007231573],"domain_scores_gemma":[0.996762,0.000299577,0.0006836021,0.00156625,0.0004753721,0.0002132211],"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":[0.00001350315,0.00001165025,0.0005230828,0.0002791595,0.0001242278,0.0001162396,0.0005147627,0.9608516,0.00004705261,0.03617273,0.00006084274,0.001285119],"study_design_scores_gemma":[0.0005606218,0.0000789101,0.00008464626,0.0003724652,0.00009305465,0.000005159633,0.0001914085,0.9948368,0.0001283528,0.001506678,0.001478488,0.0006633981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01086343,0.0001069606,0.9819923,0.0001225522,0.0006937198,0.0006254183,0.000001228844,0.0004676792,0.005126734],"genre_scores_gemma":[0.9726831,0.0002385283,0.01579254,0.0001358042,0.0002109758,0.000005154887,0.00009827048,0.00004774079,0.01078787],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9661998,"threshold_uncertainty_score":0.9996063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07805414104499778,"score_gpt":0.2066139874723149,"score_spread":0.1285598464273171,"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."}}