{"id":"W2055921164","doi":"10.1007/s10458-012-9200-2","title":"A survey of point-based POMDP solvers","year":2012,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":433,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Markov decision process; Computer science; Bellman equation; Function (biology); Observable; Value (mathematics); Point (geometry); State space; Mathematical optimization; Theoretical computer science; Space (punctuation); Scale (ratio); Markov chain; Markov process; Mathematics; Markov model; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.001216136,0.0002224049,0.0003408771,0.000140295,0.0001283623,0.0001267125,0.0005132077,0.00009352862,0.0000141041],"category_scores_gemma":[0.00007851667,0.0001979465,0.00007216677,0.0002090204,0.0000592844,0.0004050514,0.0002002165,0.0001114841,0.00006527548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008877759,"about_ca_system_score_gemma":0.00008558315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001867643,"about_ca_topic_score_gemma":0.00001281675,"domain_scores_codex":[0.9980686,0.00023435,0.0005365442,0.0003106401,0.0003368746,0.0005129657],"domain_scores_gemma":[0.9985338,0.0001364224,0.0003675697,0.0006006775,0.0001166007,0.0002449627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001328268,0.000477245,0.7583708,0.0003878576,0.0002442389,0.00001337557,0.003726563,0.2262678,0.0006338895,0.002697127,0.003855247,0.003312567],"study_design_scores_gemma":[0.000767431,0.00007488515,0.2529084,0.00005041674,0.0000140189,0.000005158865,0.00006118571,0.741416,0.0001893309,2.886011e-7,0.00428455,0.0002283648],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05566288,0.000502663,0.9407591,0.00004546454,0.001855876,0.0005434519,0.0000127305,0.0001311061,0.0004867641],"genre_scores_gemma":[0.9934121,0.00001727051,0.005330982,0.0001310175,0.0000355932,0.00001808645,0.00001985863,0.00001945481,0.001015643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9377492,"threshold_uncertainty_score":0.8072025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06430470677447479,"score_gpt":0.2858437758454526,"score_spread":0.2215390690709778,"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."}}