{"id":"W4314946886","doi":"10.1109/cdc51059.2022.9992796","title":"Inverse Optimal Control with Discount Factor for Continuous and Discrete-Time Control-Affine Systems and Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Optimal control; Bellman equation; Control theory (sociology); Mathematics; Weighting; Mathematical optimization; Linear-quadratic-Gaussian control; Quadratic equation; Linear-quadratic regulator; Computer science; Control (management)","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":[0.001092871,0.0006151921,0.001164131,0.0002871758,0.0009859144,0.0009482022,0.0007091459,0.0001177694,0.00008542189],"category_scores_gemma":[0.0002323461,0.0004932847,0.0001252343,0.0002268889,0.0002847083,0.0005359061,0.0002732376,0.0006100478,0.000008556913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001494015,"about_ca_system_score_gemma":0.0001803135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008360735,"about_ca_topic_score_gemma":0.00002810613,"domain_scores_codex":[0.995847,0.0004018989,0.0007213583,0.001259541,0.0009613227,0.0008088477],"domain_scores_gemma":[0.996681,0.001444021,0.0005275211,0.0006221597,0.0003026083,0.0004226594],"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":[0.03255627,0.0008211927,0.005937322,0.0002295399,0.002502621,0.0005491423,0.004419155,0.1550026,0.02645045,0.1421432,0.001640802,0.6277477],"study_design_scores_gemma":[0.02302336,0.004697415,0.000775094,0.00008158808,0.0001302311,0.00008517658,0.0005746139,0.9634696,0.000008605235,0.0002098057,0.006296382,0.0006481568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06640568,0.0005907413,0.927886,0.001255947,0.0003941303,0.002860462,0.0002542467,0.0001908526,0.0001619393],"genre_scores_gemma":[0.9956927,0.00006607617,0.001189866,0.0007915174,0.00008525459,0.0009107185,0.00001598979,0.00004585365,0.001202038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.929287,"threshold_uncertainty_score":0.9997519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01154954808545383,"score_gpt":0.232297176825317,"score_spread":0.2207476287398632,"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."}}