{"id":"W4283517253","doi":"10.1101/2022.06.21.496871","title":"Combining Backpropagation with Equilibrium Propagation to improve an Actor-Critic RL framework","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Backpropagation; Computer science; Reinforcement learning; Artificial intelligence; Artificial neural network; Variety (cybernetics); Task (project management); Machine learning; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009647575,0.0007044799,0.0006202629,0.0003588158,0.0005076299,0.001397069,0.00249836,0.0003830178,0.00002623046],"category_scores_gemma":[0.0001752231,0.0006785022,0.0001274075,0.00143846,0.0000768148,0.0008775466,0.003063845,0.001799744,0.00002610202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004082443,"about_ca_system_score_gemma":0.0006944757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004176014,"about_ca_topic_score_gemma":0.000001880801,"domain_scores_codex":[0.9949316,0.0004049047,0.0006746508,0.002038896,0.0009912128,0.0009586691],"domain_scores_gemma":[0.9955413,0.0001656335,0.0005407742,0.002604143,0.0005939495,0.0005541533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001897516,0.0008438845,0.005957883,0.001449385,0.0003075433,0.0004927089,0.0003465437,0.07791997,0.8824612,0.02948353,0.0003309092,0.0002166159],"study_design_scores_gemma":[0.001689848,0.003084796,0.04326875,0.003413104,0.0002017956,4.145757e-7,0.00003489526,0.6940609,0.2451295,0.0002681003,0.003014528,0.005833362],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6640329,0.0001571923,0.3296928,0.0008643438,0.002789552,0.001419904,0.00002313443,0.001009631,0.00001063979],"genre_scores_gemma":[0.9020748,0.00000913119,0.09609364,0.0005408922,0.0008145066,0.0003257966,8.038472e-7,0.0001349105,0.000005538757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6373318,"threshold_uncertainty_score":0.9996396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01406985927823535,"score_gpt":0.2341091877272333,"score_spread":0.220039328448998,"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."}}