{"id":"W4382653405","doi":"10.1002/9781119873747.ch2","title":"Markov Decision Process and Reinforcement Learning","year":2023,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Markov decision process; Reinforcement learning; Computer science; Q-learning; Markov process; Key (lock); Partially observable Markov decision process; Process (computing); Mathematical optimization; Markov chain; Bellman equation; Extension (predicate logic); Machine learning; Artificial intelligence; Markov model; 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":[0.0002654514,0.0002668625,0.0002519535,0.0003594223,0.00008859329,0.0002408923,0.0007066593,0.0002039987,0.0005590012],"category_scores_gemma":[0.0001650526,0.0002308759,0.00004304341,0.0003449477,0.00003650058,0.000157475,0.0005623726,0.0003228307,0.0006286835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000037231,"about_ca_system_score_gemma":0.00004947529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005018463,"about_ca_topic_score_gemma":0.00002041866,"domain_scores_codex":[0.9983117,0.00002599103,0.0002613187,0.0005050903,0.0005666335,0.0003292951],"domain_scores_gemma":[0.9989974,0.0001404425,0.000217963,0.0005048533,0.00003566961,0.0001036809],"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":[0.000005819365,0.000008207612,0.0005659068,0.00022659,0.00009983563,0.00004235914,0.000337246,0.4706171,0.000001969006,0.01037468,0.4191471,0.09857309],"study_design_scores_gemma":[0.0002966597,0.0001153104,0.00006437883,0.0004539158,0.00001063359,0.000006860523,0.00002901035,0.5259342,0.000008707192,0.0001214752,0.4725315,0.0004273481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[8.741936e-7,0.00005181294,0.5733636,0.00004099468,0.0002866828,0.0001570503,7.079009e-8,0.001506296,0.4245926],"genre_scores_gemma":[0.0008122298,0.0004445069,0.02431631,0.000099136,0.00009724141,0.00001823199,0.000003992483,0.0004385791,0.9737698],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5491772,"threshold_uncertainty_score":0.9414846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01150965170822089,"score_gpt":0.2672792631151527,"score_spread":0.2557696114069318,"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."}}