{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005063282,0.0002171859,0.0001511911,0.0003592349,0.0005176333,0.0005611787,0.00145409,0.00008671531,0.0002038395],"category_scores_gemma":[0.0003475939,0.0001855391,0.00009041037,0.0004140927,0.0001182707,0.0005557809,0.0002818466,0.0009150184,0.0001747551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710398,"about_ca_system_score_gemma":0.0002157337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006324796,"about_ca_topic_score_gemma":0.00003980559,"domain_scores_codex":[0.9976076,0.0001927146,0.000478996,0.0005234884,0.000834597,0.0003625433],"domain_scores_gemma":[0.9985235,0.0001630833,0.0002088102,0.0005286888,0.000499045,0.00007691718],"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":[0.00001867914,0.00002069089,0.007520299,0.000003340925,0.00002029792,0.000006164452,0.001942255,0.9346972,0.0001621565,0.05304562,0.00002929044,0.002533969],"study_design_scores_gemma":[0.0004504243,0.000127357,0.002403097,0.00008758438,0.000005412826,0.000003825444,0.0003157911,0.9955931,0.0001409408,0.0004990416,0.0001727456,0.0002006313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02236455,0.000006875473,0.9443343,0.005369393,0.0005962415,0.0002340254,3.31721e-7,0.0001927883,0.02690149],"genre_scores_gemma":[0.9910206,0.00002751913,0.004062769,0.0004029264,0.0002984362,0.00006261072,0.00003843227,0.00001914502,0.004067599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.968656,"threshold_uncertainty_score":0.7566066,"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."}}