{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002866949,0.0008989923,0.0007103664,0.0005990569,0.0007555208,0.001143369,0.001831567,0.001241974,0.003801266],"category_scores_gemma":[0.01160005,0.0003773689,0.0006020964,0.0005286086,0.00269285,0.002050977,0.002118158,0.003610357,0.0008331219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00163422,"about_ca_system_score_gemma":0.002518388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00436202,"about_ca_topic_score_gemma":0.00366703,"domain_scores_codex":[0.9988976,0.0004201556,0.00004475046,0.0002266478,0.0003080038,0.0001028346],"domain_scores_gemma":[0.9960699,0.002768501,0.0001643009,0.0005171986,0.0003391959,0.0001407451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001741935,0.0001459651,0.002330997,0.0002292528,0.00005624952,0.0001166362,0.0003192527,0.3229509,0.002835548,0.5020722,0.005505403,0.1632634],"study_design_scores_gemma":[0.00003107017,0.00007838148,0.0001613341,0.00003405076,0.00001001688,0.00004155816,0.00001769471,0.8349685,0.0008956626,0.1598281,0.003919704,0.00001385602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01179154,0.0003629281,0.9800645,0.0007432278,0.00009480755,0.00006517866,0.0000305946,0.0005625195,0.006284782],"genre_scores_gemma":[0.5760193,0.000659926,0.4138805,0.000927549,0.0001480663,0.0002651915,0.00009996811,0.0003293953,0.007670166],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00436202,"threshold_uncertainty_score":0.01516211,"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."}}