{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002399397,0.001060165,0.001442621,0.0004067844,0.0005664998,0.001040531,0.001419763,0.001202387,0.002056321],"category_scores_gemma":[0.01038532,0.0006937463,0.000715076,0.0002826195,0.00121772,0.002037109,0.002287912,0.002898424,0.0003351877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001877459,"about_ca_system_score_gemma":0.00163201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004878637,"about_ca_topic_score_gemma":0.003539463,"domain_scores_codex":[0.9984038,0.0007108953,0.00007226803,0.0002014374,0.0004521187,0.0001593948],"domain_scores_gemma":[0.9932593,0.004970686,0.00041198,0.0007036155,0.0004663239,0.0001881487],"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":[0.0001100168,0.00005878848,0.000422322,0.00005862388,0.00003120786,0.00005736813,0.00006818516,0.9586223,0.001081214,0.02368331,0.0005098414,0.01529672],"study_design_scores_gemma":[0.00001055219,0.00001133042,0.00004277737,0.000002553387,0.000002691349,0.000004638515,0.000003928825,0.9903389,0.0002094307,0.009225902,0.0001450233,0.00000232532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04247697,0.000230166,0.9520463,0.0006722909,0.00004138828,0.00007972908,0.00003297955,0.0005108326,0.003909223],"genre_scores_gemma":[0.856557,0.0001765194,0.1399903,0.0001645369,0.00005088947,0.0002657195,0.00007937842,0.0001013097,0.002614381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004878637,"threshold_uncertainty_score":0.01362199,"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."}}