{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001186984,0.0009101258,0.0008388794,0.0004400209,0.0004378112,0.001092745,0.0007230962,0.0009253589,0.00389755],"category_scores_gemma":[0.004650433,0.0004336251,0.0007793189,0.0005288586,0.001691513,0.0007982468,0.001551581,0.001984969,0.0003302931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001306595,"about_ca_system_score_gemma":0.00195929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004614852,"about_ca_topic_score_gemma":0.004538363,"domain_scores_codex":[0.9994051,0.0002545191,0.00002766632,0.0001051266,0.0001483125,0.00005929891],"domain_scores_gemma":[0.9972042,0.002316774,0.0001614114,0.00008776809,0.0001491841,0.00008072686],"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":[0.00001558622,0.00001284808,0.0001143464,0.00004656017,0.000008534321,0.00003610919,0.00004291455,0.9604667,0.0002695237,0.03094721,0.0002578547,0.007781801],"study_design_scores_gemma":[0.000007598655,0.000006555168,0.0000112196,0.000006379771,0.000001591491,0.000004629424,0.000007902911,0.9820071,0.0001372948,0.0174334,0.0003742403,0.000002045273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007055212,0.0001213671,0.9895176,0.0001940086,0.00001753448,0.00004102607,0.0000583261,0.0001842085,0.002810742],"genre_scores_gemma":[0.5682869,0.000383096,0.4254877,0.0001396751,0.00003784163,0.0005681028,0.000277705,0.0001643148,0.00465467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004614852,"threshold_uncertainty_score":0.01303858,"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."}}