{"id":"W2219400200","doi":"10.1609/aaai.v29i1.9655","title":"Approximate Linear Programming for Constrained Partially Observable Markov Decision Processes","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"Institute for Information and Communications Technology Promotion; Natural Sciences and Engineering Research Council of Canada; Ministry of Science, ICT and Future Planning","keywords":"Observable; Partially observable Markov decision process; Markov decision process; Mathematical optimization; Benchmark (surveying); Computer science; Linear programming; Suite; Sequence (biology); Dynamic programming; Controller (irrigation); State (computer science); Markov process; Mathematics; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001815158,0.001139246,0.001449325,0.0004876384,0.0004042595,0.001300149,0.0008525918,0.001233544,0.003629468],"category_scores_gemma":[0.007118206,0.0007363043,0.0006227719,0.000820516,0.001338358,0.001115359,0.001131811,0.002003606,0.0003429381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00185803,"about_ca_system_score_gemma":0.002162361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009674829,"about_ca_topic_score_gemma":0.009023144,"domain_scores_codex":[0.9987923,0.0005971325,0.00004285301,0.0001874683,0.0002543723,0.0001258869],"domain_scores_gemma":[0.9952413,0.004040951,0.0002872768,0.0001068663,0.0002346454,0.00008902016],"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":[0.00002965371,0.00001636879,0.0001123031,0.00003861411,0.00001362612,0.00002410169,0.00001987363,0.9809651,0.000142968,0.01325901,0.000246387,0.005132],"study_design_scores_gemma":[0.000004489073,0.000005009394,0.00001304031,0.000002635659,0.000001316604,0.000001847204,0.000002398013,0.9917718,0.00004503551,0.008053102,0.00009818403,0.000001147978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01351771,0.0005408189,0.9822875,0.000325892,0.00002578885,0.00005301585,0.00009621424,0.0002886916,0.002864271],"genre_scores_gemma":[0.7671506,0.0007324531,0.2246596,0.0002275508,0.00006037234,0.000511608,0.0003581854,0.000157186,0.006142464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009674829,"threshold_uncertainty_score":0.01923698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.14263682547995,"score_gpt":0.3262468132388472,"score_spread":0.1836099877588972,"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."}}