{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002125344,0.00009798315,0.00009396816,0.0002151008,0.0001037432,0.00006205772,0.0007607485,0.00007095346,0.00003003452],"category_scores_gemma":[0.00006795167,0.0001093073,0.00002879438,0.001220487,0.00007557053,0.0007659731,0.0002007034,0.0001036424,0.0001229038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008636899,"about_ca_system_score_gemma":0.00006254163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001293113,"about_ca_topic_score_gemma":0.00001836304,"domain_scores_codex":[0.9991238,0.0000472197,0.0001296925,0.0003929659,0.00009229992,0.0002140287],"domain_scores_gemma":[0.9992209,0.00004774902,0.0000906577,0.0004527606,0.000125107,0.00006282693],"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":[0.00004022615,0.0000362663,0.05693939,0.00001068251,0.000006964221,0.00007961525,0.0003567479,0.8439007,0.00003786844,0.09641014,0.0001637079,0.002017702],"study_design_scores_gemma":[0.0004157805,0.00009175183,0.005342943,0.00003258931,0.000003158251,0.000002231943,0.00003442476,0.9823663,0.0002400842,0.01096463,0.0003653443,0.000140803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1530017,0.000001997445,0.8415634,0.00003348176,0.0001560846,0.00009194637,1.236513e-7,0.00009072828,0.00506057],"genre_scores_gemma":[0.9907403,0.00000472298,0.00623057,0.00006042452,0.00003241442,1.570577e-7,0.000002180047,0.000006372859,0.002922844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8377386,"threshold_uncertainty_score":0.4457423,"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."}}