{"id":"W4404201236","doi":"10.1016/j.neucom.2024.128836","title":"Improved exploration–exploitation trade-off through adaptive prioritized experience replay","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science","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":[0.001579277,0.001069781,0.001162968,0.0005262641,0.0005363352,0.001037255,0.001999278,0.001012729,0.002170969],"category_scores_gemma":[0.006685399,0.0005337689,0.0003902737,0.0003248692,0.0007568327,0.002056286,0.001873323,0.001455362,0.0004432095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005733482,"about_ca_system_score_gemma":0.001756822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002286825,"about_ca_topic_score_gemma":0.002827493,"domain_scores_codex":[0.9991484,0.000161373,0.00006732869,0.0002138777,0.0002636407,0.0001454576],"domain_scores_gemma":[0.9978702,0.0008941391,0.0003169607,0.0002467546,0.0004200709,0.0002518608],"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":[0.001008567,0.0007248751,0.006583192,0.0002466899,0.0001697744,0.0002954277,0.0004983196,0.5730988,0.0213419,0.01258202,0.002876817,0.3805735],"study_design_scores_gemma":[0.00005572071,0.0002180759,0.0004670809,0.00001530814,0.00002052971,0.00006151719,0.0000284478,0.9920437,0.003187883,0.003279223,0.0006079765,0.00001459284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0927371,0.0005591126,0.9022538,0.0003075945,0.00008774129,0.000157366,0.00004091697,0.001464483,0.002392014],"genre_scores_gemma":[0.8974664,0.0001492276,0.09973657,0.0002034294,0.00003992327,0.0001956634,0.00006628023,0.00009718501,0.002045303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002286825,"threshold_uncertainty_score":0.008352101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04017482748357579,"score_gpt":0.288268733131924,"score_spread":0.2480939056483482,"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."}}