{"id":"W4397048993","doi":"10.48550/arxiv.2405.09999","title":"Reward Centering","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; DeepMind; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Psychology","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":[0.002853385,0.001264909,0.001404197,0.000645504,0.0006382671,0.001436952,0.002271954,0.00112007,0.006328708],"category_scores_gemma":[0.01418887,0.0004089419,0.0006169833,0.0005688822,0.00166866,0.002683578,0.002309038,0.002513067,0.001215975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001694594,"about_ca_system_score_gemma":0.001958616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002412694,"about_ca_topic_score_gemma":0.001979175,"domain_scores_codex":[0.998064,0.0006061087,0.0000922085,0.0005319995,0.0005082643,0.0001974032],"domain_scores_gemma":[0.9947253,0.002560677,0.0005868434,0.0009384144,0.0008606769,0.0003281211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004036856,0.0003320731,0.002509959,0.0003413616,0.0001328401,0.0001061964,0.0002207557,0.5312665,0.006059004,0.1339791,0.006795191,0.3178534],"study_design_scores_gemma":[0.00004020353,0.000129156,0.0002525918,0.00003798615,0.00003095054,0.00005555626,0.00001356828,0.9523626,0.00404628,0.03907639,0.003932319,0.00002239768],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01355496,0.0005344027,0.9798356,0.0002499975,0.0001275802,0.00007476949,0.00004115278,0.0009142033,0.004667346],"genre_scores_gemma":[0.5776055,0.0005321493,0.414327,0.0003539851,0.0001558452,0.0002423597,0.0001643235,0.0003954379,0.006223497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006328708,"threshold_uncertainty_score":0.02117163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07759720201491045,"score_gpt":0.1875801099626226,"score_spread":0.1099829079477122,"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."}}