{"id":"W4367060663","doi":"10.48550/arxiv.2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Successor cardinal; Representation (politics); Value (mathematics); Artificial intelligence; Function (biology); Carry (investment); Feature learning; Object (grammar); Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001620883,0.0008320644,0.0007719233,0.0004264694,0.0003586361,0.000948446,0.001500354,0.001162271,0.003487101],"category_scores_gemma":[0.008483458,0.0003969307,0.0004187426,0.0004034206,0.001312957,0.002962815,0.001963267,0.001960412,0.0004665327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008479833,"about_ca_system_score_gemma":0.0007087445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009321825,"about_ca_topic_score_gemma":0.0009468812,"domain_scores_codex":[0.9996015,0.0001547064,0.00001774662,0.0000984686,0.00008138451,0.00004613493],"domain_scores_gemma":[0.9976943,0.001392343,0.0002283167,0.0003075204,0.0001994767,0.0001780362],"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":[0.0002637214,0.0002339378,0.001349687,0.0001306898,0.00005342981,0.0001017162,0.0001504215,0.7476091,0.00555663,0.09947185,0.002650155,0.1424286],"study_design_scores_gemma":[0.00001456335,0.00004808368,0.00006587854,0.00000726178,0.000004267808,0.00001401715,0.000005541155,0.9682136,0.0008139947,0.03040628,0.0004025325,0.000004017318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05852667,0.0001788305,0.9366651,0.000346047,0.0000554563,0.00006926137,0.0000603776,0.0005589741,0.003539211],"genre_scores_gemma":[0.7814595,0.0002161319,0.2144727,0.0002156224,0.00005119957,0.0002158726,0.0001272903,0.0001288915,0.003112669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003487101,"threshold_uncertainty_score":0.01166552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09279756993421001,"score_gpt":0.2157709403239721,"score_spread":0.1229733703897621,"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."}}