{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008828277,0.0003754003,0.000281336,0.0004301082,0.0004976669,0.0002502834,0.002115135,0.0002318339,0.000009043283],"category_scores_gemma":[0.0001430977,0.0003687055,0.0002111872,0.000954802,0.00006041805,0.0002746982,0.002748926,0.0009108444,0.0003952854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007109483,"about_ca_system_score_gemma":0.0003383011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001491025,"about_ca_topic_score_gemma":0.00005225749,"domain_scores_codex":[0.9975414,0.0002015029,0.0003799244,0.001045175,0.000297432,0.0005345487],"domain_scores_gemma":[0.9976355,0.0001152977,0.0004554098,0.001264317,0.0003540266,0.0001754843],"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":[0.00001633149,0.00002818604,0.0002700216,0.00006973355,0.00005022469,0.00002142827,0.0004537227,0.9857033,0.00004117084,0.01238442,0.0007191662,0.0002422279],"study_design_scores_gemma":[0.0005271811,0.0001134155,0.0001620827,0.0001494404,0.00005335483,4.876151e-7,0.00004316497,0.9970587,0.00005136439,0.0004520148,0.0009856044,0.000403156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00189524,0.000006990958,0.9938086,0.001554052,0.0005273857,0.001101209,0.000002047476,0.0006986153,0.0004059171],"genre_scores_gemma":[0.9567081,0.00002446744,0.02305002,0.0002399473,0.00005513636,0.00001275719,0.00006996006,0.00003622441,0.01980338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9707585,"threshold_uncertainty_score":0.9998765,"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."}}