{"id":"W4378768695","doi":"10.48550/arxiv.2305.17198","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social 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":[0.001165254,0.00107069,0.001399329,0.0003402872,0.0004861539,0.0008967252,0.001605736,0.001425663,0.003045018],"category_scores_gemma":[0.003690114,0.000576306,0.0005767992,0.0003123328,0.001202737,0.000944059,0.001716249,0.002181477,0.0005792282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007884863,"about_ca_system_score_gemma":0.001948488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003609283,"about_ca_topic_score_gemma":0.003338833,"domain_scores_codex":[0.9994067,0.0002076037,0.00002286791,0.0001693242,0.000116675,0.00007681937],"domain_scores_gemma":[0.9984107,0.0008842403,0.0002058964,0.0001998384,0.0001550469,0.000144152],"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":[0.00003092628,0.0000326981,0.0002105423,0.0000401155,0.00001527466,0.00004153192,0.00003412444,0.9750556,0.0005851353,0.009889832,0.0007552734,0.01330901],"study_design_scores_gemma":[0.000009378692,0.00001855714,0.00003036634,0.000003461219,0.000002254108,0.000009474406,0.000005949606,0.9944111,0.0001518014,0.005067142,0.000288155,0.000002294764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005884011,0.00005764412,0.9912368,0.0002041618,0.00002324595,0.00004043612,0.00003386998,0.0002448566,0.002274937],"genre_scores_gemma":[0.7012683,0.000115715,0.2930601,0.0001938982,0.00005516446,0.0002981352,0.0001471368,0.0001419608,0.004719497],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003609283,"threshold_uncertainty_score":0.01018661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1368835793866977,"score_gpt":0.2271378487904828,"score_spread":0.09025426940378514,"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."}}