{"id":"W7124257082","doi":"10.65109/ehmm3042","title":"Search-Improved Game-Theoretic Multiagent Reinforcement Learning in General and Negotiation Games","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","funders":"","keywords":"Reinforcement learning; Negotiation; Generative grammar; Bayesian probability; Test (biology); Representation (politics); Bayesian inference; Social learning; Reinforcement","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":[0.002956496,0.0006195985,0.001114438,0.0005061921,0.0004226452,0.0007853115,0.001475548,0.0007684042,0.001602872],"category_scores_gemma":[0.009186825,0.0003929336,0.000514633,0.000415458,0.001231213,0.001241866,0.001234985,0.001293046,0.0001982003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094862,"about_ca_system_score_gemma":0.001264678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005555228,"about_ca_topic_score_gemma":0.005259837,"domain_scores_codex":[0.9991907,0.0004942573,0.00003085675,0.0001057606,0.00009704327,0.00008132694],"domain_scores_gemma":[0.9959735,0.003027543,0.0003266079,0.0002396262,0.000270964,0.0001617766],"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":[0.00003350688,0.00003694954,0.0006378268,0.00001879516,0.00001932182,0.00001795957,0.00003771652,0.9825802,0.0001984215,0.007367345,0.00017359,0.008878319],"study_design_scores_gemma":[0.0000079974,0.00001355979,0.00004725435,0.000001596922,0.000002148087,0.000003113999,0.000002801296,0.9968701,0.00007089713,0.002914901,0.00006405505,0.000001614486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1555994,0.0002740588,0.8392604,0.0004208236,0.00003299926,0.0001079025,0.00005121808,0.0003274594,0.003925818],"genre_scores_gemma":[0.9254081,0.00006597881,0.07332395,0.00007357268,0.00001216281,0.0001065774,0.00005008591,0.00003246771,0.0009272473],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005555228,"threshold_uncertainty_score":0.01563561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0221885923684442,"score_gpt":0.2702905656329382,"score_spread":0.248101973264494,"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."}}