{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001218163,0.0003350916,0.0008869733,0.0003178804,0.0003353594,0.0006085044,0.001211553,0.001206458,0.002049196],"category_scores_gemma":[0.005567675,0.0004006556,0.0003104154,0.0004019459,0.0009110816,0.0009477445,0.0009757273,0.001177397,0.0001591312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008964006,"about_ca_system_score_gemma":0.0006726672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005002498,"about_ca_topic_score_gemma":0.004667523,"domain_scores_codex":[0.999716,0.0001333717,0.00001347957,0.00005187813,0.00004062423,0.0000446607],"domain_scores_gemma":[0.997977,0.001600724,0.0001101796,0.00008649512,0.0001554934,0.000070136],"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":[0.00004569807,0.00003648701,0.0003287379,0.00001995935,0.00001736299,0.00002928184,0.0000411627,0.9724892,0.0005322261,0.01136302,0.0003026469,0.01479426],"study_design_scores_gemma":[0.000004877747,0.000005978775,0.00002714698,0.000001368284,0.000001373553,0.00000183285,0.000001752461,0.9970711,0.0000694189,0.00278131,0.00003274551,0.000001006364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1848392,0.0005297714,0.8095276,0.0005785468,0.00008632797,0.00005129819,0.00003732546,0.0002729246,0.004076976],"genre_scores_gemma":[0.9276383,0.0001138703,0.06902976,0.0001080087,0.00002867518,0.00009375601,0.00003755453,0.00003977223,0.002910336],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005002498,"threshold_uncertainty_score":0.009946764,"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."}}