{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001208441,0.0002930063,0.0003453929,0.0001163085,0.0002391861,0.0004943446,0.002442492,0.0001213989,0.000011362],"category_scores_gemma":[0.003762657,0.0002205814,0.000117557,0.0008743454,0.0002969973,0.00069811,0.0004720172,0.0002525411,0.00003550281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006259207,"about_ca_system_score_gemma":0.0005112284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001228573,"about_ca_topic_score_gemma":0.000006280997,"domain_scores_codex":[0.9972799,0.00001571855,0.0007819302,0.000583825,0.0007772198,0.0005614366],"domain_scores_gemma":[0.9961715,0.0002796153,0.0006053637,0.0003799662,0.002375432,0.000188118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004459426,0.0002895094,0.0005631301,0.0004576813,0.00004872285,0.00000111497,0.002946838,0.03716252,0.006099163,0.7679531,0.0005354869,0.1834968],"study_design_scores_gemma":[0.0001129917,0.0006296638,0.00001104108,0.0004143202,0.00002065934,0.000005686569,0.0006314941,0.7439793,0.1943689,0.05824236,0.001263229,0.0003202975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01017303,0.00002237963,0.9831963,0.001556539,0.000535936,0.001255222,0.000003476012,0.0002095125,0.003047612],"genre_scores_gemma":[0.8021566,0.00001515776,0.197114,0.0001399486,0.00008968475,0.0001204261,0.000001544993,0.00002143287,0.0003411271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7919836,"threshold_uncertainty_score":0.899505,"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."}}