{"id":"W1503109067","doi":"","title":"Point-Based Value Iteration for Constrained POMDPs","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov decision process; Mathematical optimization; Bellman equation; Computer science; Dynamic programming; Minimax; Linear programming; Value (mathematics); Scalability; Function (biology); Point (geometry); Markov process; 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":[0.002537624,0.001096443,0.001798306,0.0006454653,0.0005842845,0.001197674,0.001465477,0.001349862,0.003936662],"category_scores_gemma":[0.007809177,0.0008369017,0.001026304,0.0007417257,0.001905629,0.001738619,0.001980408,0.002411762,0.0004142665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001568152,"about_ca_system_score_gemma":0.00191628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005064134,"about_ca_topic_score_gemma":0.004529928,"domain_scores_codex":[0.9984376,0.0007137562,0.00007937229,0.000233433,0.0003918999,0.0001438438],"domain_scores_gemma":[0.9960419,0.00308714,0.0002284284,0.0001684671,0.0003571541,0.0001168843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003460664,0.00001982255,0.0001827694,0.0000633154,0.00001978221,0.00003248925,0.00004410922,0.9418346,0.0003309456,0.04531677,0.0003561072,0.01176471],"study_design_scores_gemma":[0.000008368846,0.00001112902,0.00001336174,0.000005495384,0.000001976799,0.000003986475,0.000003954188,0.9808853,0.0001320142,0.01867451,0.0002565525,0.000003325603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004368687,0.00008759745,0.9938578,0.00006882051,0.00001538347,0.00004154045,0.00002955632,0.0001135834,0.001417093],"genre_scores_gemma":[0.5050951,0.0003396738,0.4902057,0.0001263399,0.00004414968,0.0006564924,0.0002132766,0.0001737082,0.003145539],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005064134,"threshold_uncertainty_score":0.0134204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02092790281422207,"score_gpt":0.2662145478222802,"score_spread":0.2452866450080581,"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."}}