{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001599489,0.0007816156,0.0009772792,0.000399421,0.0005678575,0.001194145,0.001585892,0.001168287,0.00307649],"category_scores_gemma":[0.008501643,0.0004010217,0.0005886287,0.0003003688,0.002016449,0.001976062,0.002233317,0.001849854,0.0003397177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109217,"about_ca_system_score_gemma":0.001036011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003504563,"about_ca_topic_score_gemma":0.003148392,"domain_scores_codex":[0.9995224,0.0002337981,0.00001639868,0.00007477235,0.00008621138,0.00006631271],"domain_scores_gemma":[0.9970855,0.002210674,0.0002046296,0.0001434329,0.0001823603,0.0001733958],"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":[0.00003669662,0.00005052984,0.0004448927,0.00004613462,0.00002962033,0.00007045545,0.00007897036,0.8745092,0.000805672,0.115054,0.0005834785,0.008290391],"study_design_scores_gemma":[0.000007501078,0.00001091507,0.00002311081,0.000002946915,0.000001673514,0.000004518467,0.00000654918,0.9673227,0.00008176048,0.03241044,0.0001258774,0.000002065811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07601224,0.0002545338,0.9138418,0.0006198656,0.0000558242,0.0000772249,0.00003064964,0.0001673239,0.008940591],"genre_scores_gemma":[0.9034896,0.0002346796,0.08990064,0.0002706469,0.00005669312,0.0002326585,0.0000586316,0.00008242887,0.005674048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003504563,"threshold_uncertainty_score":0.01029187,"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."}}