{"id":"W7124241411","doi":"10.65109/ldqz4728","title":"Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Alberta; Vector Institute","funders":"","keywords":"Reinforcement learning; Sample complexity; Set (abstract data type); Sample (material); Convergence (economics); Action (physics); Error-driven learning; State (computer science)","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","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00278261,0.001123844,0.001071383,0.001578277,0.0009669736,0.001182829,0.002634848,0.000617789,0.001462646],"category_scores_gemma":[0.002229959,0.001239081,0.0004381451,0.00368425,0.0001891821,0.001434011,0.004107869,0.003690703,0.009335685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009480825,"about_ca_system_score_gemma":0.0004084435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003224835,"about_ca_topic_score_gemma":0.0003153431,"domain_scores_codex":[0.9889557,0.001084068,0.002520149,0.002262042,0.002515525,0.002662559],"domain_scores_gemma":[0.9953185,0.001300406,0.001005132,0.001466865,0.0002667583,0.0006423268],"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":[0.00004346514,0.00009609875,0.1406922,0.00006058517,0.0001287104,0.0002480099,0.01225591,0.8345076,0.0005490636,0.0002680571,0.0002053235,0.01094487],"study_design_scores_gemma":[0.00415179,0.0006597966,0.05610912,0.00040725,0.00003592986,0.000004083077,0.004136723,0.9243468,0.0005833302,0.00001945149,0.008279756,0.001265946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08978131,0.0001640785,0.9008216,0.0004902465,0.002578158,0.001293919,0.00000117501,0.001411116,0.003458398],"genre_scores_gemma":[0.9244621,0.001041392,0.008062466,0.0002418027,0.0001707672,0.00009970058,0.0001536269,0.0001337351,0.06563434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8927591,"threshold_uncertainty_score":0.999854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05499245184937777,"score_gpt":0.2792454045787129,"score_spread":0.2242529527293352,"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."}}