{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00143667,0.0009498391,0.0009830638,0.0005735346,0.0004082281,0.000930621,0.002211918,0.001063132,0.003722406],"category_scores_gemma":[0.005453466,0.0006869199,0.0005617317,0.0004279583,0.001343001,0.002308736,0.001494411,0.002307512,0.0004764848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001442971,"about_ca_system_score_gemma":0.0009990794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007197576,"about_ca_topic_score_gemma":0.007163219,"domain_scores_codex":[0.9994454,0.0001974575,0.00003109268,0.0001449298,0.0001117456,0.00006938646],"domain_scores_gemma":[0.9969573,0.002035275,0.0002201879,0.0002846406,0.0003323311,0.0001702697],"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":[0.00009314675,0.00005790468,0.0004065842,0.00003485623,0.00002671016,0.00004074943,0.00004599307,0.9674913,0.0005314327,0.005505816,0.0006199781,0.02514557],"study_design_scores_gemma":[0.000008409462,0.0000131403,0.00002429074,0.000002638388,0.000002376039,0.000003880655,0.000002455796,0.9963716,0.0001400517,0.00330974,0.0001187709,0.00000262377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06539355,0.000423912,0.9277636,0.0004741472,0.00008017661,0.00008318424,0.00017546,0.001561584,0.004044459],"genre_scores_gemma":[0.9237292,0.0001639472,0.07202865,0.0001768343,0.00004170854,0.0002230557,0.0002152664,0.000113372,0.003307914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007197576,"threshold_uncertainty_score":0.01431137,"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."}}