{"id":"W4319985622","doi":"10.1002/cjce.24878","title":"Multi‐agent reinforcement learning for process control: Exploring the intersection between fields of reinforcement learning, control theory, and game theory","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Alberta","keywords":"Reinforcement learning; Marl; Controller (irrigation); Computer science; Process (computing); Function (biology); Control (management); Intersection (aeronautics); Reinforcement; Control system; Control theory (sociology); Control engineering; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002736303,0.0001824469,0.0002965824,0.0001800112,0.0001904821,0.0001278621,0.0007068613,0.0000701323,0.000007048304],"category_scores_gemma":[0.001545684,0.0001262965,0.0001366224,0.0002598064,0.00009169948,0.0002569984,0.00005777498,0.0007110381,0.000001674209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001577799,"about_ca_system_score_gemma":0.0001662097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007331636,"about_ca_topic_score_gemma":0.000007005961,"domain_scores_codex":[0.9984316,0.0001065945,0.0005782439,0.0001426856,0.0003069809,0.0004339054],"domain_scores_gemma":[0.9977845,0.001230595,0.0003568714,0.0002089221,0.0001937433,0.0002253521],"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":[0.00003704029,0.000001148346,0.000267154,0.00006011706,0.0001518505,0.000003269505,0.003311654,0.9886706,0.001310111,0.004415771,0.00001437893,0.001756854],"study_design_scores_gemma":[0.001191255,0.0002447757,0.0002997172,0.0001885755,0.00007726764,0.00001774299,0.0002920929,0.9898759,0.006805534,0.0003132712,0.0005330041,0.0001608961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09416737,0.00007030266,0.9047008,0.0004099629,0.0002910605,0.0002865697,3.969292e-7,0.00004116602,0.00003237476],"genre_scores_gemma":[0.9992668,0.000008043477,0.0002873468,0.00007339719,0.0001681761,0.00003222679,0.000001863702,0.00002201549,0.0001401394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9050994,"threshold_uncertainty_score":0.5150221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02187824374282683,"score_gpt":0.2356329742072273,"score_spread":0.2137547304644005,"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."}}