{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002510757,0.0001870628,0.0001575836,0.000449541,0.0001623215,0.0003921928,0.0004523451,0.00008267279,0.00001432703],"category_scores_gemma":[0.00008165457,0.0001631072,0.0001091453,0.0007490865,0.00002869372,0.0002558775,0.0001398583,0.0001016903,0.000008325547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000119545,"about_ca_system_score_gemma":0.0002717657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000259322,"about_ca_topic_score_gemma":0.000001369213,"domain_scores_codex":[0.9986897,0.00006056239,0.0002626004,0.0004875034,0.000214451,0.0002852031],"domain_scores_gemma":[0.9993112,0.00008351475,0.00006073302,0.000321872,0.0001359532,0.00008673417],"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":[0.00001250334,0.0000278295,9.66684e-7,0.00004066111,0.000009371325,0.000003081689,0.0002872132,0.8669465,0.000096557,0.1143351,0.002350533,0.01588968],"study_design_scores_gemma":[0.0003357682,0.00008701406,0.000001711494,0.0000350719,0.00001020334,0.00001407532,0.000006914471,0.991167,0.001187773,0.003435598,0.003514819,0.0002040445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001425975,0.0000921733,0.9919119,0.003231199,0.0001964386,0.0006300894,0.00001056226,0.002513378,0.001271667],"genre_scores_gemma":[0.05165919,0.00001256622,0.9465932,0.0003976511,0.0001369178,0.00005023241,0.00007231569,0.00002176404,0.001056115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1242205,"threshold_uncertainty_score":0.6651317,"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."}}