{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000378541,0.0002932607,0.0002754249,0.000111311,0.0003606796,0.0009980057,0.0008472255,0.00009014559,0.000004041844],"category_scores_gemma":[0.00008664223,0.0002875196,0.0001446567,0.000990359,0.00004642201,0.00180531,0.0002528425,0.0003439386,0.00005590551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006879908,"about_ca_system_score_gemma":0.0001189009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001930213,"about_ca_topic_score_gemma":0.000001288995,"domain_scores_codex":[0.9972613,0.0002206897,0.0005917671,0.001021583,0.0004054918,0.0004991533],"domain_scores_gemma":[0.9986581,0.0004482499,0.0001533689,0.0005590757,0.0000777678,0.0001034558],"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":[0.0000707123,0.0002900415,0.0001572687,0.0004334998,0.0001581751,0.0007079192,0.1632009,0.03136735,0.03001584,0.2679313,0.01026058,0.4954064],"study_design_scores_gemma":[0.0003082118,0.000152231,0.0001333998,0.0002220509,0.000007023779,0.00009851382,0.0004486648,0.9682406,0.001240775,0.002084678,0.02669876,0.0003651239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02602732,0.0005923427,0.9654344,0.001045752,0.002708879,0.0004430263,0.000003911326,0.00186215,0.001882262],"genre_scores_gemma":[0.9626916,0.00001475389,0.03622157,0.0003747221,0.0005082351,0.00004493325,0.00001013003,0.00002964296,0.0001044011],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368732,"threshold_uncertainty_score":0.9999577,"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."}}