{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003010325,0.001180822,0.00184924,0.0007727923,0.0006367284,0.001635842,0.002467385,0.001375916,0.001934755],"category_scores_gemma":[0.005009709,0.0007871126,0.001189964,0.0009228187,0.001790194,0.001979548,0.002340951,0.002028353,0.0002823187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001368394,"about_ca_system_score_gemma":0.002010024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002272166,"about_ca_topic_score_gemma":0.001973744,"domain_scores_codex":[0.9978741,0.001114017,0.0000809323,0.0002951518,0.0004605541,0.0001752162],"domain_scores_gemma":[0.9971265,0.002019733,0.0002642294,0.0001652368,0.0002498079,0.0001743874],"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":[0.00003495374,0.0000504555,0.000174011,0.00007048296,0.00004053367,0.00007299742,0.00007808481,0.9180762,0.0006568148,0.06084831,0.000442956,0.01945417],"study_design_scores_gemma":[0.00001061516,0.00002143211,0.00002433336,0.000005858901,0.000005801011,0.00001296562,0.000007855568,0.9744492,0.0001441555,0.02482385,0.0004879532,0.000005940051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001719438,0.00009291098,0.9973344,0.00009323016,0.0000180941,0.00002158784,0.000004897523,0.00003476541,0.0006807503],"genre_scores_gemma":[0.4651992,0.000545579,0.5307378,0.0002415434,0.0001428052,0.0004398961,0.00004952306,0.0001303144,0.002513438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003010325,"threshold_uncertainty_score":0.01592028,"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."}}