{"id":"W3164770271","doi":"10.1007/s00521-021-06104-5","title":"Lucid dreaming for experience replay: refreshing past states with the current policy","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Army Research Office; Defense Advanced Research Projects Agency; Office of Naval Research; Future of Life Institute; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Lockheed Martin; Robert Bosch (Australia) Pty; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; State (computer science); Reinforcement learning; Work (physics); Dream; Artificial intelligence; Programming language; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001371611,0.0006774157,0.0007122882,0.0002724558,0.0004529637,0.00112672,0.001385655,0.0009387459,0.005273156],"category_scores_gemma":[0.01199778,0.0004416978,0.0003932667,0.0002121172,0.0009651493,0.002897227,0.002064477,0.002254892,0.0007225362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003895025,"about_ca_system_score_gemma":0.0008194259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002820684,"about_ca_topic_score_gemma":0.003609664,"domain_scores_codex":[0.9995758,0.0001624072,0.00002688192,0.0001074577,0.00006903385,0.00005842451],"domain_scores_gemma":[0.9980896,0.001015089,0.0001247432,0.0003855822,0.0001877881,0.0001972784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004215343,0.0009219866,0.008112253,0.0006468697,0.0003882712,0.0008655676,0.002953494,0.3791716,0.02036084,0.05710418,0.02655031,0.4987092],"study_design_scores_gemma":[0.00011938,0.0002706665,0.000726485,0.00006115089,0.00006458907,0.0001057493,0.0002636356,0.9399108,0.004130339,0.05100632,0.003294123,0.00004673298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1779896,0.001843864,0.7966172,0.004097873,0.0008164892,0.0001973559,0.0003699147,0.004792992,0.01327471],"genre_scores_gemma":[0.9360926,0.0002245462,0.06049116,0.000345999,0.00004813153,0.00008203987,0.000148296,0.0001550654,0.00241215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005273156,"threshold_uncertainty_score":0.01764047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01889025861605372,"score_gpt":0.3080537549947229,"score_spread":0.2891634963786692,"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."}}