{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001473387,0.0006062682,0.0006647852,0.0007543457,0.0002730092,0.0008643133,0.00327113,0.0003342045,0.00001049314],"category_scores_gemma":[0.0002857036,0.000563241,0.0001095231,0.0009335928,0.0003377503,0.001151969,0.001014685,0.0006448117,0.00001237217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003737996,"about_ca_system_score_gemma":0.001956591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005926765,"about_ca_topic_score_gemma":0.0009986133,"domain_scores_codex":[0.9953367,0.00003224713,0.0008491843,0.001853625,0.000932658,0.0009956548],"domain_scores_gemma":[0.9970079,0.0007480091,0.0003300439,0.001129698,0.0005876988,0.0001966196],"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":[0.00002531407,0.00004410544,0.0001010474,0.0001013694,0.000006002394,0.00003055169,0.0004717075,0.3076995,0.0001242655,0.002440579,0.00002177196,0.6889338],"study_design_scores_gemma":[0.0002929409,0.0001358811,0.00004477022,0.0009920711,0.000005859324,0.00002480477,1.183748e-7,0.7717099,0.001381746,0.2237645,0.001043976,0.0006033895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006683948,0.0009988266,0.9960116,0.0004586195,0.0008629631,0.0005547925,0.00001440078,0.0001387156,0.0002917411],"genre_scores_gemma":[0.07318371,0.0001975326,0.924937,0.001101312,0.0003170297,0.00002208138,0.000006672202,0.00004513148,0.0001895965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6883304,"threshold_uncertainty_score":0.9996819,"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."}}