{"id":"W2490120274","doi":"10.4018/978-1-60960-165-2.ch003","title":"An Introduction to Fully and Partially Observable Markov Decision Processes","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Management science; Partially observable Markov decision process; Markov decision process; Focus (optics); Markov process; Software deployment; Markov chain; Observable; Markov model; Risk analysis (engineering); Machine learning; Mathematics; Software engineering; Engineering; Business","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"],"consensus_categories":[],"category_scores_codex":[0.0002501401,0.0004025435,0.0003560605,0.00009658736,0.0001564643,0.0004527041,0.001061725,0.0002831488,0.0000314484],"category_scores_gemma":[0.0001019299,0.0003953493,0.00005487468,0.00005439779,0.00006318021,0.0003573531,0.0005095677,0.0002318343,0.0001541317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133982,"about_ca_system_score_gemma":0.0002993968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002937489,"about_ca_topic_score_gemma":0.00007411018,"domain_scores_codex":[0.9977009,0.00002108123,0.0004295816,0.0009204844,0.0005415623,0.0003864178],"domain_scores_gemma":[0.9979581,0.00003564232,0.0002375098,0.001115089,0.0003510714,0.0003026435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006350566,0.000008509704,0.0000433179,0.00006759894,0.00003282406,0.0000239627,0.0001696191,0.00531804,0.00002434344,0.9471382,0.00413347,0.04297653],"study_design_scores_gemma":[0.0006935771,0.002471534,0.0004298045,0.0005502161,0.0001336812,0.0002010491,0.00001194383,0.007619786,0.000406732,0.4484986,0.5369644,0.002018681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001043997,0.00008392948,0.5950894,0.0001854141,0.0008055984,0.0003934179,0.000005180416,0.0002582,0.4030745],"genre_scores_gemma":[0.1453805,0.00008677877,0.5229146,0.003480846,0.004765762,0.0001073549,0.00002781706,0.000256191,0.3229801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5328309,"threshold_uncertainty_score":0.9998499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02260650668927809,"score_gpt":0.2481189723978673,"score_spread":0.2255124657085892,"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."}}