{"id":"W7124272070","doi":"10.65109/emmn5327","title":"Neural Population Learning beyond Symmetric Zero-Sum Games","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Convergence (economics); Suite; Population; Domain (mathematical analysis); Transfer of learning; Scale (ratio); Control (management); Stability (learning theory)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008947849,0.0005344134,0.0004281359,0.001266378,0.0005040785,0.003763251,0.001115412,0.0002651327,0.0005804429],"category_scores_gemma":[0.0005452263,0.0005168289,0.0002696432,0.005399271,0.00009191062,0.0022193,0.0008548439,0.001305134,0.001692172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002738406,"about_ca_system_score_gemma":0.0001525178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002189089,"about_ca_topic_score_gemma":0.000002820916,"domain_scores_codex":[0.9952658,0.000318202,0.0009622743,0.001201695,0.001236687,0.001015355],"domain_scores_gemma":[0.9979848,0.0005530267,0.0002216151,0.0007622204,0.0002014023,0.0002769001],"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":[0.000003464052,0.00001510681,0.004387699,0.0001860056,0.00006374076,0.00005506489,0.0005802228,0.7498056,0.00004679531,0.07751165,0.001393103,0.1659515],"study_design_scores_gemma":[0.0001830229,0.0003403108,0.01470076,0.0001826156,0.00006954132,0.00004969902,0.00004655531,0.9706962,0.00005868865,0.000770924,0.01232274,0.0005790188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006853831,0.003081252,0.9439968,0.001634205,0.007001653,0.0003629566,7.006802e-7,0.001158973,0.03590964],"genre_scores_gemma":[0.9225474,0.0002894872,0.008840471,0.0002940575,0.0003851771,0.000007581276,0.00002534641,0.0000635511,0.06754693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9351563,"threshold_uncertainty_score":0.9997283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01797043713864816,"score_gpt":0.2646179451708731,"score_spread":0.2466475080322249,"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."}}