{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00160073,0.001105702,0.0008661395,0.000461475,0.0003057445,0.0008650305,0.001608692,0.001205183,0.002139805],"category_scores_gemma":[0.003802129,0.0004716738,0.0003963764,0.0003321138,0.000985818,0.001044237,0.001168746,0.001769743,0.0005318183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007115958,"about_ca_system_score_gemma":0.000923408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00463917,"about_ca_topic_score_gemma":0.003599876,"domain_scores_codex":[0.9996752,0.000121583,0.00001847277,0.00005632768,0.00008822387,0.00004029041],"domain_scores_gemma":[0.9988027,0.0006844394,0.00009500457,0.00009454216,0.0002531385,0.00007016684],"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":[0.00004721561,0.0000296925,0.000283739,0.00003294126,0.00004340113,0.00005620966,0.00002373097,0.9636957,0.001991145,0.01029476,0.0008280491,0.02267336],"study_design_scores_gemma":[0.000002571205,0.000005760085,0.000008426998,0.000001552297,0.000002046857,0.000002526627,4.629733e-7,0.9985113,0.000186038,0.001188018,0.00009002455,0.00000136181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02172783,0.0003228739,0.9728804,0.0004693,0.0001009791,0.00003736849,0.00002117965,0.0008493218,0.003590705],"genre_scores_gemma":[0.8267026,0.0002279458,0.1673646,0.0002116865,0.00009399158,0.0001143843,0.00004945489,0.000161954,0.005073477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00463917,"threshold_uncertainty_score":0.009224355,"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."}}