{"id":"W2953351167","doi":"10.48550/arxiv.1704.02544","title":"A Linearly Relaxed Approximate Linear Program for Markov Decision Processes","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Linear programming; Constraint (computer-aided design); Markov decision process; Mathematical optimization; Markov chain; Markov process; Computer science; Mathematics; Linear approximation; Applied mathematics; Nonlinear system; Statistics; Physics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000528398,0.0004832771,0.0005072813,0.0002930248,0.0005316405,0.0007267402,0.004448615,0.0005015477,0.000008055029],"category_scores_gemma":[0.0008496785,0.0005190704,0.0002917618,0.0004099533,0.0001681143,0.0007511855,0.003195568,0.0007334796,0.00006431244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001723698,"about_ca_system_score_gemma":0.0006164256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002907422,"about_ca_topic_score_gemma":0.00001121082,"domain_scores_codex":[0.9972245,0.00006582381,0.000365621,0.00150893,0.0002163828,0.0006187294],"domain_scores_gemma":[0.995312,0.0003565674,0.0008100546,0.002542609,0.0007589706,0.0002197833],"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":[0.0001171857,0.0001375005,0.0007759879,0.0007020407,0.0001087641,0.0001021499,0.0001813549,0.9794956,0.000004067915,0.008480804,0.0005250179,0.009369525],"study_design_scores_gemma":[0.0008378939,0.0002952149,0.0001527748,0.0004077576,0.00008206572,0.000004113554,0.0000141646,0.9833447,0.00007617917,0.007573009,0.006629424,0.0005827176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008903763,0.00006165313,0.9858714,0.00009337676,0.0008381617,0.001808425,0.00001231272,0.0007819255,0.001628981],"genre_scores_gemma":[0.6590937,0.0003516108,0.3323417,0.00005370603,0.0002338956,0.00002971997,0.00007112075,0.00006682101,0.007757724],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6535298,"threshold_uncertainty_score":0.9997261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08128687683702827,"score_gpt":0.2421828787003502,"score_spread":0.1608960018633219,"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."}}