{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001552627,0.0001131622,0.0002160222,0.00003841106,0.0001649841,0.0001626799,0.0002414069,0.00006500234,0.00002859574],"category_scores_gemma":[0.000027578,0.00009551433,0.00005910187,0.000453713,0.00003318271,0.0002152245,0.00008266674,0.0001932653,9.573114e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002317348,"about_ca_system_score_gemma":0.0000458708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001978185,"about_ca_topic_score_gemma":2.055734e-7,"domain_scores_codex":[0.9990022,0.00002988017,0.0003936413,0.000214706,0.0001786822,0.0001808756],"domain_scores_gemma":[0.9990689,0.0001688412,0.0002978928,0.0001718572,0.0001450449,0.0001475049],"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":[0.00001847424,0.0001387378,0.00001189115,0.000004743811,0.00001657809,0.000003917203,0.00008400567,0.9298858,0.002807305,0.006079399,0.001050865,0.05989826],"study_design_scores_gemma":[0.0003768378,0.00006608397,0.0000251056,0.00000541715,0.00001451492,0.00003002292,0.00002017492,0.9960802,0.001460415,0.0008433266,0.0009631591,0.0001147116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005814203,0.0005432174,0.9972359,0.001028778,0.0001334645,0.00008908747,0.000001123354,0.00002387891,0.0003631178],"genre_scores_gemma":[0.7198624,0.0005348574,0.2783225,0.0009825242,0.0002187694,0.000009404761,0.00001510036,0.00001294143,0.00004144217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.719281,"threshold_uncertainty_score":0.3894961,"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."}}