{"id":"W3176644733","doi":"10.1016/j.jprocont.2021.06.004","title":"Online reinforcement learning for a continuous space system with experimental validation","year":2021,"lang":"en","type":"article","venue":"Journal of Process Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; State space; Artificial intelligence; Machine learning; Heuristic; Trajectory; Asynchronous communication; Mathematics","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":[0.0003998541,0.0001515686,0.0003646653,0.0001023565,0.0001358768,0.0002464539,0.0003931304,0.00004843112,0.000008192088],"category_scores_gemma":[0.0001960377,0.0001199733,0.0001041694,0.0002044138,0.00001996864,0.0006327141,0.00003806313,0.0002360059,0.000002223259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001436513,"about_ca_system_score_gemma":0.0003356149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001280388,"about_ca_topic_score_gemma":4.163905e-7,"domain_scores_codex":[0.9983656,0.00007565694,0.0005530326,0.0001800153,0.0005744759,0.0002511871],"domain_scores_gemma":[0.9974665,0.0001377154,0.0009618938,0.0001792038,0.001151092,0.0001035857],"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":[0.0001324949,0.00006479533,0.0004470805,0.0001149706,0.0001165417,0.0000650903,0.0006871404,0.9926145,0.002697857,0.002650895,0.00005944122,0.0003492062],"study_design_scores_gemma":[0.006315806,0.001865128,0.00006925403,0.0004098555,0.00007095499,0.0005058831,0.002770472,0.9479387,0.03845737,0.00001241803,0.001365491,0.0002186728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01695284,0.0002638839,0.981521,0.0004485813,0.0002509847,0.0002557512,3.984002e-7,0.00004733323,0.0002592696],"genre_scores_gemma":[0.9808493,0.000003902843,0.01822815,0.000107919,0.0001920225,0.00001474875,0.000003965759,0.00001521061,0.0005848281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9638964,"threshold_uncertainty_score":0.4892369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0123185152797147,"score_gpt":0.2662024340434771,"score_spread":0.2538839187637624,"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."}}