{"id":"W7124292505","doi":"10.65109/hdvm4783","title":"Monitored Markov Decision Processes","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Ask price; Partially observable Markov decision process; Formalism (music); Task (project management); Markov process","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002009706,0.001257218,0.001422957,0.0006212927,0.0006299345,0.001838376,0.002104402,0.001748886,0.005928978],"category_scores_gemma":[0.008176247,0.0005470372,0.0009885926,0.0008437298,0.002076642,0.002598977,0.00168354,0.002694047,0.0007925878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001824385,"about_ca_system_score_gemma":0.001353853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003967456,"about_ca_topic_score_gemma":0.004706759,"domain_scores_codex":[0.9983747,0.0007256209,0.00009237947,0.000420264,0.0002242092,0.0001627862],"domain_scores_gemma":[0.9937999,0.004455753,0.0006342337,0.0004776079,0.0003682112,0.0002642231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001095249,0.00007055519,0.001365757,0.0001464601,0.0000644966,0.0002476929,0.0001470149,0.3490483,0.0005970729,0.627695,0.002491187,0.01801701],"study_design_scores_gemma":[0.00003573766,0.00002866354,0.0001330004,0.00001971281,0.0000150039,0.00003683252,0.00001571236,0.7113428,0.0001768766,0.2856635,0.002518788,0.00001337438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01131503,0.0007065993,0.9788691,0.0009677703,0.0001407494,0.00007999206,0.0004149987,0.0003621919,0.007143578],"genre_scores_gemma":[0.7726099,0.001604609,0.2115468,0.0005333891,0.0002889871,0.0004617903,0.0007810472,0.00009232856,0.01208106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005928978,"threshold_uncertainty_score":0.01983434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01665031143990564,"score_gpt":0.2815242047084176,"score_spread":0.264873893268512,"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."}}