{"id":"W4404986356","doi":"10.48550/arxiv.2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Real-time computing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.001266247,0.001142292,0.0008564109,0.0003643135,0.0003609789,0.0008556613,0.001804746,0.0009508088,0.002843215],"category_scores_gemma":[0.005723603,0.0005181632,0.0004033246,0.0003257407,0.0009963585,0.00228627,0.001336519,0.002413092,0.001013347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001105288,"about_ca_system_score_gemma":0.001455877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004237676,"about_ca_topic_score_gemma":0.005324899,"domain_scores_codex":[0.9995201,0.0001188929,0.00003144493,0.0001119012,0.0001506094,0.00006703001],"domain_scores_gemma":[0.998772,0.0005573725,0.0001235487,0.0002440557,0.0002194334,0.0000835247],"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":[0.0003687731,0.0002374916,0.001730277,0.0001574739,0.00008723416,0.000109381,0.0001077311,0.7047428,0.009188993,0.03043967,0.006478163,0.2463519],"study_design_scores_gemma":[0.0000124945,0.00003746918,0.00007899477,0.000006009717,0.00000531899,0.00001443773,0.000004080681,0.9916957,0.003006272,0.004465789,0.0006684408,0.000004936702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02747045,0.0003997691,0.9650703,0.0003595419,0.0001122404,0.00007833755,0.00007561872,0.003041294,0.003392477],"genre_scores_gemma":[0.7260426,0.0003207584,0.265924,0.0003325493,0.00007442935,0.0002420869,0.0002351458,0.0003954857,0.006432944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004237676,"threshold_uncertainty_score":0.009511471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05825574032702813,"score_gpt":0.253147211500646,"score_spread":0.1948914711736178,"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."}}