{"id":"W2011231614","doi":"10.1145/1329125.1329178","title":"Reducing the complexity of multiagent reinforcement learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Reinforcement learning; Initialization; Computer science; Function (biology); Artificial intelligence; Representation (politics); Class (philosophy); Multi-agent system; Function approximation; Mathematical optimization; Sample complexity; Computational complexity theory; Action (physics); Mathematics; Algorithm; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.001466873,0.0001105775,0.0001278617,0.00007772654,0.0002195041,0.00006040313,0.0008749124,0.00003408472,0.00008684521],"category_scores_gemma":[0.0001421458,0.00007504864,0.0000705817,0.0003166308,0.0001937741,0.0001875872,0.0004318653,0.0002374578,0.00004235564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005418831,"about_ca_system_score_gemma":0.00003160392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001478422,"about_ca_topic_score_gemma":0.000005114139,"domain_scores_codex":[0.9985097,0.00005271903,0.0004409475,0.0001967846,0.0004697312,0.0003300897],"domain_scores_gemma":[0.9988457,0.000188892,0.0002280379,0.0005720491,0.0001026182,0.00006268542],"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":[0.00000336764,0.000008026256,0.000447187,0.000008765644,0.00001454738,0.0000018245,0.001140585,0.8736878,0.0009772364,0.1194749,0.0001457949,0.004089995],"study_design_scores_gemma":[0.0002125503,0.0001171352,0.00404967,0.00002031652,0.000004750614,0.000005428678,0.0002537595,0.9749985,0.01602997,0.0001864158,0.003999318,0.0001221933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003454938,0.0000166226,0.9570084,0.0004680517,0.0002211341,0.0001675779,2.123004e-8,0.0001231696,0.03854015],"genre_scores_gemma":[0.9383803,0.000006171235,0.05835102,0.0001764488,0.00003362291,0.000001626312,0.000001214859,0.000005862938,0.003043741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9349254,"threshold_uncertainty_score":0.3060395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06037491723560053,"score_gpt":0.2889836438266715,"score_spread":0.228608726591071,"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."}}