{"id":"W2132911866","doi":"10.1007/11564096_58","title":"Using Rewards for Belief State Updates in Partially Observable Markov Decision Processes","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Computer science; Markov decision process; State (computer science); Action (physics); Observable; Artificial intelligence; Markov chain; Markov process; Markov model; Machine learning; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007583967,0.001410461,0.002199221,0.001214333,0.0008978508,0.003163441,0.002434799,0.002399633,0.004449727],"category_scores_gemma":[0.05103496,0.001515195,0.001042705,0.001410883,0.002252866,0.007244778,0.003049046,0.00448591,0.0005502517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002120608,"about_ca_system_score_gemma":0.001546064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00496387,"about_ca_topic_score_gemma":0.004087612,"domain_scores_codex":[0.99606,0.002348438,0.0002410995,0.0004138968,0.0006898346,0.0002467591],"domain_scores_gemma":[0.940722,0.05455948,0.001381685,0.001534987,0.001223284,0.0005785872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00040809,0.0001110756,0.0008982703,0.0002389618,0.00008745074,0.0001057412,0.0002786739,0.6216618,0.0005961476,0.2987665,0.001976149,0.07487109],"study_design_scores_gemma":[0.00001716599,0.00001435883,0.00005113745,0.00001418821,0.000009673925,0.000006883071,0.000006347771,0.871107,0.0001856963,0.128366,0.0002112078,0.00001031314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01041468,0.0003331811,0.9872335,0.000308387,0.00008930119,0.00002969752,0.00006533732,0.0003190538,0.001206808],"genre_scores_gemma":[0.6320909,0.0009742202,0.359871,0.0002069011,0.0003038854,0.0003016301,0.0004250453,0.0003991193,0.005427279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007583967,"threshold_uncertainty_score":0.04010832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04877212309381557,"score_gpt":0.297007662227469,"score_spread":0.2482355391336535,"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."}}