{"id":"W2923023063","doi":"","title":"Modeling the Long Term Future in Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Term (time); Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001515609,0.0005987287,0.0009521006,0.0004287819,0.0003537154,0.001281627,0.001262801,0.001148651,0.002614483],"category_scores_gemma":[0.006533797,0.0005099331,0.0004560767,0.0005126983,0.001030904,0.00235754,0.00106726,0.001867951,0.0002447881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234292,"about_ca_system_score_gemma":0.000968948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008656397,"about_ca_topic_score_gemma":0.008916649,"domain_scores_codex":[0.9995641,0.0002041249,0.00002087786,0.00009369943,0.00006094865,0.00005635479],"domain_scores_gemma":[0.997852,0.001520175,0.000212989,0.0001046416,0.0001953218,0.0001148597],"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":[0.00004797834,0.00002301572,0.0005217587,0.00002988103,0.00002090517,0.00003467367,0.00004240293,0.9583411,0.0002089687,0.03267341,0.0003193416,0.007736503],"study_design_scores_gemma":[0.000006006694,0.000009444351,0.00003693736,0.000003446316,0.000004091029,0.000004182461,0.00000364058,0.98544,0.00003962165,0.01435796,0.00009193231,0.000002745026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08642178,0.0007325049,0.9076887,0.00100227,0.00009572246,0.00003256849,0.0001690775,0.0002471446,0.003610187],"genre_scores_gemma":[0.9663367,0.0003112814,0.03040026,0.00008139247,0.0000318125,0.00008269882,0.0001069782,0.0000321661,0.002616769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008656397,"threshold_uncertainty_score":0.01721197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05336023462993137,"score_gpt":0.3395181485785783,"score_spread":0.2861579139486469,"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."}}