{"id":"W4221102161","doi":"10.1007/s11227-022-04305-w","title":"Improved reinforcement learning in cooperative multi-agent environments using knowledge transfer","year":2022,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Reinforcement learning; Abstraction; State space; Convergence (economics); Process (computing); Artificial intelligence; Fuse (electrical); Mechanism (biology); State (computer science); Space (punctuation); Transfer of learning; Class (philosophy); Machine learning; Distributed computing; Algorithm","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":[0.003164259,0.0002000866,0.0003458741,0.0001968652,0.0005948789,0.00008656122,0.00123075,0.00003223481,0.0000240824],"category_scores_gemma":[0.00005165192,0.0001562095,0.000129945,0.0004178034,0.00003808739,0.0004331738,0.0005233195,0.0008395471,0.000005362364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000663947,"about_ca_system_score_gemma":0.0001514589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009160618,"about_ca_topic_score_gemma":0.000006950218,"domain_scores_codex":[0.996942,0.001061974,0.0009062244,0.0002025255,0.0004659696,0.0004213314],"domain_scores_gemma":[0.999163,0.0002096581,0.0002108674,0.0002619211,0.0000621539,0.00009245532],"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":[0.00002687469,0.0001392385,0.0005779192,0.000007175645,0.00006008949,0.00002822778,0.01108816,0.9133945,0.07241602,0.000085269,0.000009370585,0.002167121],"study_design_scores_gemma":[0.002199656,0.0002437949,0.0005987154,0.00005556427,0.00002355083,0.0001888482,0.002369285,0.9914036,0.001832289,0.000002992336,0.0009085783,0.0001731598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3396178,0.0004228895,0.6591298,0.0001050788,0.0004476084,0.0002326427,9.224887e-7,0.00001251213,0.00003076746],"genre_scores_gemma":[0.9982406,0.00001338557,0.001453881,0.00008525295,0.00008640969,0.000004391854,0.000001561393,0.0000162601,0.00009820368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6586229,"threshold_uncertainty_score":0.6370038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03410398160610389,"score_gpt":0.2610866262253376,"score_spread":0.2269826446192337,"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."}}