{"id":"W3208016380","doi":"10.3389/frai.2022.805823","title":"Investigation of independent reinforcement learning algorithms in multi-agent environments","year":2022,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Reinforcement learning; Algorithm; Artificial intelligence; Machine learning","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":[0.0067811,0.001525566,0.001716811,0.001065557,0.0008715758,0.001379032,0.002715024,0.00153556,0.00161917],"category_scores_gemma":[0.02494975,0.0008322531,0.0009963433,0.0007210267,0.001911815,0.003121131,0.001810941,0.002612897,0.0003367757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00122359,"about_ca_system_score_gemma":0.002204841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002462789,"about_ca_topic_score_gemma":0.001763345,"domain_scores_codex":[0.9969442,0.001277122,0.0001411147,0.0006789545,0.0006381954,0.0003203819],"domain_scores_gemma":[0.9776764,0.01570194,0.00189496,0.002265223,0.001482589,0.0009788751],"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":[0.000243354,0.0002564983,0.003292132,0.0001286355,0.0001398356,0.00006373267,0.0001122556,0.9300897,0.0008238506,0.01655428,0.000574548,0.04772117],"study_design_scores_gemma":[0.00002423572,0.00007746738,0.0002264305,0.000007700205,0.00001092521,0.00001586245,0.00001085425,0.9940818,0.0003341845,0.004995292,0.000209223,0.000005900372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1392541,0.0009685248,0.8523829,0.0004354843,0.00007940399,0.0002287312,0.00005402575,0.0006325693,0.0059642],"genre_scores_gemma":[0.8585444,0.0002820868,0.1389398,0.0001253495,0.00004410111,0.000207064,0.0001227846,0.00009415767,0.001640304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0067811,"threshold_uncertainty_score":0.03586233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05814036785717878,"score_gpt":0.2710809898253303,"score_spread":0.2129406219681515,"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."}}