{"id":"W4413278563","doi":"10.1109/icfpt64416.2024.11113396","title":"HEPPO: Hardware-Efficient Proximal Policy Optimization a Universal Pipelined Architecture for Generalized Advantage Estimation","year":2024,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Architecture; Computer architecture; Parallel computing; Hardware architecture; Computer hardware; Estimation; Embedded system; Operating system; Software; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004970856,0.0004588954,0.0004925872,0.0002594366,0.0002472324,0.0005379677,0.001481147,0.0005599708,0.00484176],"category_scores_gemma":[0.001191634,0.0003652053,0.0002883955,0.0002725301,0.0004252432,0.0006060015,0.0008867993,0.001162403,0.0009861788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005171029,"about_ca_system_score_gemma":0.001439683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003327356,"about_ca_topic_score_gemma":0.004544017,"domain_scores_codex":[0.9997675,0.0000450792,0.00001376478,0.00005041318,0.00008550696,0.00003789716],"domain_scores_gemma":[0.9997275,0.00009942611,0.00002579671,0.00005606561,0.00006162684,0.00002961751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004307235,0.0001518947,0.001167837,0.0002108187,0.00008572526,0.0001504078,0.0001055546,0.6006574,0.02223472,0.03337143,0.006773819,0.3346597],"study_design_scores_gemma":[0.00001846336,0.00005465965,0.00009375503,0.000005571829,0.000005667102,0.00001706039,0.00000345543,0.9927147,0.002888103,0.002335788,0.001857052,0.000005654501],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008029705,0.0001361371,0.9867251,0.00009000801,0.00004584327,0.00005111783,0.00004324554,0.001989186,0.002889659],"genre_scores_gemma":[0.4709772,0.0002228099,0.5220327,0.0001835896,0.00005211929,0.0002326832,0.0002106504,0.0002004835,0.005887907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00484176,"threshold_uncertainty_score":0.01619732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01082188503368793,"score_gpt":0.2822848092987674,"score_spread":0.2714629242650795,"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."}}