{"id":"W3177052905","doi":"10.1007/s10710-021-09418-4","title":"Evolving hierarchical memory-prediction machines in multi-task reinforcement learning","year":2021,"lang":"en","type":"preprint","venue":"Genetic Programming and Evolvable Machines","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Computer science; Task (project management); Variety (cybernetics); Encoding (memory); Artificial intelligence; Action (physics); ENCODE; Identification (biology); Salient; Machine learning; Decomposition; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005437939,0.000457799,0.0004684333,0.0003069311,0.0004982697,0.0007453943,0.0007580493,0.0002843508,0.00002067609],"category_scores_gemma":[0.0001169338,0.0004547401,0.0001423273,0.0004944846,0.0001081987,0.0002409504,0.002162695,0.001168692,0.000005884041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140974,"about_ca_system_score_gemma":0.0002007282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001510093,"about_ca_topic_score_gemma":0.0001428732,"domain_scores_codex":[0.9968749,0.0001937178,0.0006911196,0.001206071,0.0004215207,0.0006126405],"domain_scores_gemma":[0.9985392,0.00009825144,0.0002296032,0.0007700265,0.0001594911,0.000203434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008461037,0.0003672976,0.04961298,0.0004970619,0.0000967442,0.00006236131,0.002748429,0.3072914,0.0003271035,0.0004086725,0.0001135833,0.6384659],"study_design_scores_gemma":[0.000481734,0.00007145394,0.04317596,0.0002574459,0.00002713079,0.00005683787,0.00009472567,0.9533973,0.0000150085,0.001094675,0.0009149443,0.000412721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08806127,0.01205783,0.8970006,0.0007345426,0.0006454467,0.000797232,0.000006442455,0.0004603449,0.0002362794],"genre_scores_gemma":[0.5288731,0.0006379309,0.4690252,0.00004988829,0.0001945811,0.0004773755,0.0001628272,0.00003020986,0.0005489209],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.646106,"threshold_uncertainty_score":0.9997904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0154498512321424,"score_gpt":0.2573528990363186,"score_spread":0.2419030478041762,"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."}}