{"id":"W3205279237","doi":"10.1109/icra48506.2021.9560793","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Machine learning; Dynamics (music); Control (management); Robot; Plan (archaeology); State (computer science); Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002077978,0.0001704706,0.0001755428,0.00005299298,0.0001566844,0.0002716755,0.0004688488,0.00006292381,0.0001128713],"category_scores_gemma":[0.00004874063,0.0001421924,0.00005511145,0.000355228,0.0000398042,0.0003066557,0.0002213372,0.0003055156,0.00006726746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005295557,"about_ca_system_score_gemma":0.0002714263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004553381,"about_ca_topic_score_gemma":0.000003742797,"domain_scores_codex":[0.9984462,0.00005575907,0.000242318,0.0003782443,0.0004795319,0.0003979009],"domain_scores_gemma":[0.9989162,0.0000892989,0.0001030394,0.0005542627,0.0002238412,0.0001133195],"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":[0.000006053025,0.00001012275,0.0008339873,0.000006755699,0.00001766324,0.00003357527,0.0001120257,0.9725203,0.00006160229,0.0247868,0.0003857276,0.001225365],"study_design_scores_gemma":[0.0005975203,0.000144488,0.00005159661,0.00003088979,0.000008221526,0.00001116685,0.00003552347,0.9934202,0.001727346,0.00003323664,0.003715273,0.0002245771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009312479,0.00002470088,0.9460952,0.0004268584,0.00009113607,0.0000912578,3.409354e-8,0.0003286611,0.05201085],"genre_scores_gemma":[0.7842017,0.000004719999,0.1871125,0.00100409,0.00003159924,0.000009224893,0.000009729843,0.00001421973,0.02761224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7832705,"threshold_uncertainty_score":0.5798439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01245078320415947,"score_gpt":0.2208727236929298,"score_spread":0.2084219404887704,"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."}}