{"id":"W2891166116","doi":"10.48550/arxiv.1811.00429","title":"Temporal Regularization in Markov Decision Process","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Regularization (linguistics); Markov decision process; Reinforcement learning; Computer science; Exploit; Artificial intelligence; Machine learning; Markov process; Mathematical optimization; Partially observable Markov decision process; Markov chain; Regularization perspectives on support vector machines; Inverse problem; Mathematics; Markov model; Statistics","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":[0.004554663,0.0009595617,0.001484976,0.0006427149,0.0007089765,0.001348285,0.001191808,0.00190123,0.00407268],"category_scores_gemma":[0.01463649,0.0005860495,0.0008684356,0.0008056529,0.002118501,0.001884351,0.001532878,0.00289501,0.0003627531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002394247,"about_ca_system_score_gemma":0.001722351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007760595,"about_ca_topic_score_gemma":0.005670252,"domain_scores_codex":[0.9977496,0.001177244,0.00009689582,0.0003837516,0.0004160946,0.0001763705],"domain_scores_gemma":[0.988031,0.01015582,0.0007266156,0.0003164727,0.0005215519,0.0002486075],"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":[0.0000824286,0.0000547151,0.001037658,0.0001434049,0.00005849669,0.0001279658,0.0001317674,0.6060611,0.0006416257,0.3726742,0.001360208,0.01762637],"study_design_scores_gemma":[0.00001290794,0.00001978165,0.00009734948,0.00001245472,0.000005876162,0.00001059642,0.000005717717,0.8916541,0.0001010232,0.1076158,0.0004567654,0.00000757577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01862475,0.001185357,0.9723397,0.00137854,0.0001027207,0.00005382689,0.0001027818,0.0001682061,0.006044091],"genre_scores_gemma":[0.8898076,0.001529222,0.09998108,0.0004568769,0.0002204209,0.0003201824,0.0001731647,0.00008399674,0.007427487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007760595,"threshold_uncertainty_score":0.02408761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03660652369230544,"score_gpt":0.1961727198969281,"score_spread":0.1595661962046227,"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."}}