{"id":"W3187079608","doi":"10.24963/ijcai.2021/562","title":"Symbolic Dynamic Programming for Continuous State MDPs with Linear Program Transitions","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Discretization; Computer science; Piecewise linear function; Dynamic programming; Linear programming; Mathematical optimization; Operator (biology); Bellman equation; Piecewise; State (computer science); Algorithm; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001393589,0.0001560903,0.0001922337,0.00006014883,0.0001756221,0.0003330501,0.0003493798,0.00004110664,0.00001053072],"category_scores_gemma":[0.00002704919,0.0001308978,0.00007986242,0.0004626043,0.00005352167,0.0002864721,0.00006246797,0.0001365282,0.00001752925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000337197,"about_ca_system_score_gemma":0.000169377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006137231,"about_ca_topic_score_gemma":0.00004095222,"domain_scores_codex":[0.9986577,0.00003325269,0.0002367443,0.000378275,0.0002430117,0.0004510037],"domain_scores_gemma":[0.9990157,0.00006530359,0.00007162853,0.0004489025,0.0002956747,0.000102778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003038736,0.0005012628,0.0005660296,0.0002232231,0.0002403406,0.0001432552,0.003176115,0.460818,0.0005890492,0.02956704,0.0002057463,0.5039396],"study_design_scores_gemma":[0.0007753188,0.0006903937,0.0002223642,0.00004815766,0.00002428795,0.0000607046,0.0001627406,0.9726967,0.0008167618,0.0001462029,0.02408211,0.0002742885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003955292,0.00002880415,0.992264,0.001054062,0.0001018659,0.000911455,0.000002164489,0.0007360329,0.0009462744],"genre_scores_gemma":[0.1820418,0.000006893549,0.8122968,0.0001916936,0.00002022349,0.0002524989,0.00003862727,0.00002264912,0.005128828],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5118787,"threshold_uncertainty_score":0.5337859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01060705909788936,"score_gpt":0.2697420779943324,"score_spread":0.2591350188964431,"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."}}