{"id":"W4361273506","doi":"10.3390/systems11040180","title":"It’s All about Reward: Contrasting Joint Rewards and Individual Reward in Centralized Learning Decentralized Execution Algorithms","year":2023,"lang":"en","type":"article","venue":"Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Reinforcement learning; Variance (accounting); Computer science; Joint (building); Function (biology); Foraging; Machine learning; Artificial intelligence; Value (mathematics); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002946761,0.000334644,0.0005869637,0.0004312926,0.0002272391,0.0007087045,0.0006332737,0.0002136507,0.000006029716],"category_scores_gemma":[0.0006503545,0.0003361146,0.00009496938,0.0009738241,0.00007527207,0.0005539913,0.0004393699,0.0005560879,0.00008969922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000221723,"about_ca_system_score_gemma":0.0001170625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003047171,"about_ca_topic_score_gemma":0.00001033191,"domain_scores_codex":[0.9955892,0.0006445806,0.00100599,0.000726933,0.0009375833,0.001095688],"domain_scores_gemma":[0.9984636,0.0002648488,0.0004332569,0.0004781206,0.0001152579,0.0002448713],"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":[0.00006732863,0.00007312545,0.02926717,0.0007876604,0.0003813128,0.0005543931,0.04204963,0.8944834,0.003826042,0.005606839,0.01102602,0.01187704],"study_design_scores_gemma":[0.002962283,0.0001730692,0.01932574,0.0008502858,0.00003330493,0.00008882512,0.001394688,0.9425386,0.0001982996,0.00009468614,0.03171716,0.0006230975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1273049,0.002141781,0.852792,0.003249296,0.006165422,0.002796969,0.00001452639,0.002937103,0.002597949],"genre_scores_gemma":[0.9918698,0.0007447284,0.005475141,0.0002105892,0.0001183233,0.00008041253,0.00007377163,0.0000501164,0.001377092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8645649,"threshold_uncertainty_score":0.9999091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06219908550440429,"score_gpt":0.2892080950814729,"score_spread":0.2270090095770686,"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."}}