{"id":"W2067564749","doi":"10.1142/s0218213012500030","title":"STOCHASTIC RESOURCE ALLOCATION IN MULTIAGENT ENVIRONMENTS: AN APPROACH BASED ON DISTRIBUTED Q-VALUES AND BOUNDED REAL-TIME DYNAMIC PROGRAMMING","year":2012,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence Tools","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Bounded function; A priori and a posteriori; Mathematical optimization; Heuristic; Convergence (economics); Set (abstract data type); Multi-agent system; Distributed computing; Resource allocation; Dynamic programming; Distributed algorithm; Resource (disambiguation); Reduction (mathematics); Algorithm; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001220583,0.0001671801,0.0001848858,0.0003198959,0.00007386302,0.0004046272,0.0008258861,0.00006923993,0.0000153874],"category_scores_gemma":[0.0005052697,0.0001580124,0.00006236262,0.000179006,0.0000993965,0.001214958,0.0001045114,0.0002688086,0.00002117554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003570625,"about_ca_system_score_gemma":0.00005681536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001270879,"about_ca_topic_score_gemma":0.000001178765,"domain_scores_codex":[0.9977093,0.0001678471,0.0007573171,0.0002247794,0.0008439124,0.0002968058],"domain_scores_gemma":[0.9987251,0.000258652,0.0004746688,0.0002397718,0.0001449372,0.0001568598],"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":[0.00009170237,0.0004124713,0.0001809433,0.000003488767,0.00002841596,0.000008793347,0.0009957398,0.8813365,0.001305289,0.003020694,0.000004803353,0.1126112],"study_design_scores_gemma":[0.000106456,0.0002506158,0.00240654,0.00007362416,0.000009782869,0.00002444256,0.0003573642,0.99482,0.001085649,0.0005928483,0.0001158752,0.0001568034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05462029,0.00001864657,0.9444301,0.0003747581,0.0002699706,0.0001946292,0.000002973031,0.00002258007,0.00006608905],"genre_scores_gemma":[0.9271466,0.00001065879,0.07254519,0.0000945936,0.0001213545,0.000008305212,0.00003738161,0.00001194495,0.00002402728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8725262,"threshold_uncertainty_score":0.6443558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03907911182316321,"score_gpt":0.3112756167984046,"score_spread":0.2721965049752414,"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."}}