{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005420669,0.0003814502,0.0002670162,0.0003400043,0.0002498369,0.003866858,0.001625143,0.0001914928,0.0007430856],"category_scores_gemma":[0.0005348395,0.000323606,0.0001325681,0.002292814,0.000111378,0.001605922,0.0008895232,0.0004608936,0.003622631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001350988,"about_ca_system_score_gemma":0.0008724726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001640619,"about_ca_topic_score_gemma":0.00000148273,"domain_scores_codex":[0.9965351,0.00006104481,0.0006663252,0.0009769598,0.001093545,0.0006670697],"domain_scores_gemma":[0.9975693,0.0008806642,0.00008150575,0.0009278282,0.0003099415,0.000230798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002165058,0.00004948794,0.0005021495,0.001225452,0.0001137012,0.0002472172,0.001580794,0.2956007,0.00006228613,0.01371005,0.03081472,0.6560717],"study_design_scores_gemma":[0.0001404817,0.0002247853,0.0002505577,0.001010494,0.00003058711,0.00003660712,0.00004650218,0.9277019,0.0006857571,0.0008412953,0.0686314,0.0003996255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005457199,0.005099826,0.9500319,0.001003505,0.006887988,0.0003065821,0.000001109458,0.0007381404,0.03538517],"genre_scores_gemma":[0.8091331,0.001396813,0.1345969,0.0002296432,0.0005946605,0.00001440767,0.000002754348,0.00005009938,0.05398171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8154351,"threshold_uncertainty_score":0.9999216,"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."}}