{"id":"W3201820699","doi":"10.1109/tpami.2022.3215769","title":"Continuous-Time Fitted Value Iteration for Robust Policies","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Bellman equation; Discretization; Reinforcement learning; Leverage (statistics); Optimal control; Mathematical optimization; Computer science; Robustness (evolution); Dynamic programming; Mathematics; Artificial intelligence","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":[0.0003152773,0.0001780628,0.0002652528,0.0005442717,0.0006006101,0.0002327854,0.0004820657,0.00003270365,0.0002646976],"category_scores_gemma":[0.000007189205,0.0001761346,0.0002337397,0.0008965275,0.00003687456,0.0002280989,0.0000134522,0.0002326279,0.00001796712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000059809,"about_ca_system_score_gemma":0.00001980887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004888483,"about_ca_topic_score_gemma":0.00005786038,"domain_scores_codex":[0.9985867,0.00009336352,0.0003594756,0.0004067745,0.0003177029,0.0002360443],"domain_scores_gemma":[0.9991148,0.0001935682,0.0001433774,0.0004099849,0.00007690192,0.00006140042],"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":[0.00000833039,0.00005354299,0.0001439509,0.000006963935,0.0002210655,0.000001371607,0.0003633045,0.9196454,0.0001873562,0.0002079278,0.00003433441,0.07912651],"study_design_scores_gemma":[0.00009677,0.0002359298,0.0001523959,0.000004595259,0.0002226522,0.000006627733,0.00004465233,0.9885537,0.009947155,0.00007601038,0.0004661484,0.0001933843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008783853,0.00002355093,0.9976381,0.0007987852,0.0002030975,0.0002309509,0.00004209501,0.0001101397,0.00007488499],"genre_scores_gemma":[0.9912379,0.00002693689,0.005917741,0.001085447,0.00002150273,0.00009383781,0.00002525139,0.00001287796,0.001578482],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9917204,"threshold_uncertainty_score":0.7182559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02069552346583519,"score_gpt":0.2601900016066627,"score_spread":0.2394944781408275,"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."}}