{"id":"W2111467524","doi":"","title":"An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward","year":2009,"lang":"en","type":"article","venue":"TUbilio (Technical University of Darmstadt)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Parameterized complexity; Markov decision process; Mathematical optimization; Computer science; Maximization; Linear-quadratic-Gaussian control; Computation; Gaussian process; Heuristics; Optimization problem; Algorithm; Quadratic equation; Markov process; Gaussian; Mathematics; Optimal control","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":[0.0001439743,0.0001579112,0.0002566882,0.0001611467,0.000173152,0.00007036768,0.0008926056,0.0001138205,0.00001370502],"category_scores_gemma":[0.00006390767,0.0001463995,0.00005538294,0.0007286624,0.0001009262,0.00112129,0.00005799372,0.0001132354,0.000002253935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004831058,"about_ca_system_score_gemma":0.0002896103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001239977,"about_ca_topic_score_gemma":0.00002821245,"domain_scores_codex":[0.9987401,0.00002897724,0.0001995805,0.0004963525,0.0003011696,0.0002338117],"domain_scores_gemma":[0.9986703,0.0001416594,0.0001839986,0.0004570895,0.0004213498,0.0001255554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005079454,0.0008879417,0.0005177398,0.0001752495,0.00002212985,0.00006592671,0.0009082229,0.0001626572,0.001698471,0.01123195,0.0007417382,0.98308],"study_design_scores_gemma":[0.02745899,0.04959856,0.1241837,0.003632659,0.0007007768,0.0007582424,0.00725707,0.3199466,0.07037447,0.3792188,0.009857174,0.007012961],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01529827,0.0000372167,0.9830139,0.000372931,0.00002326894,0.000380269,0.00001318858,0.0002472802,0.0006136849],"genre_scores_gemma":[0.4724028,0.00003632502,0.5274454,0.00005619083,0.00001160091,7.915946e-7,0.00001450414,0.000004799278,0.00002765134],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9760671,"threshold_uncertainty_score":0.5969999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005562707577122003,"score_gpt":0.2138742374957114,"score_spread":0.2083115299185894,"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."}}