{"id":"W4205304882","doi":"10.23952/jano.3.2021.3.06","title":"Improved sample efficiency by episodic memory hit ratio deep Q-networks","year":2021,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Episodic memory; Sample (material); Computer science; Psychology; Neuroscience; Chemistry; Cognition","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001856484,0.00072359,0.001035628,0.0003550788,0.0003302091,0.000692063,0.001672713,0.000968338,0.002124308],"category_scores_gemma":[0.005549446,0.0003748333,0.0003283776,0.000302164,0.0007691141,0.001511008,0.001266651,0.001095156,0.0003426172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007074953,"about_ca_system_score_gemma":0.001333326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002543629,"about_ca_topic_score_gemma":0.002922063,"domain_scores_codex":[0.999396,0.000186503,0.00004493808,0.000136894,0.0001400063,0.00009568979],"domain_scores_gemma":[0.998171,0.001058002,0.0001895636,0.0001943295,0.0002694799,0.0001176523],"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":[0.0004391721,0.0003065566,0.003095892,0.000140692,0.00008464509,0.0001351902,0.0001269124,0.6809681,0.006681158,0.0187801,0.002596158,0.2866455],"study_design_scores_gemma":[0.00002465956,0.00005608886,0.0001061958,0.000004543559,0.000008134132,0.00001646462,0.000004242501,0.9957538,0.0009981261,0.002779037,0.0002445589,0.000004198052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0673583,0.0005555066,0.9283635,0.0002848781,0.00005425082,0.00007549102,0.00003670661,0.0008824351,0.002388992],"genre_scores_gemma":[0.8652185,0.0001874172,0.1308902,0.0003594917,0.00003847968,0.0001215074,0.00008812589,0.0001032192,0.002993081],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002543629,"threshold_uncertainty_score":0.009818196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005171540651790802,"score_gpt":0.2061447720945865,"score_spread":0.2009732314427957,"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."}}