{"id":"W2159752377","doi":"10.1177/1059712313511648","title":"Multi-timescale nexting in a reinforcement learning robot","year":2014,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Innovates - Technology Futures","keywords":"Reinforcement learning; Computer science; Laptop; Generalization; Temporal difference learning; Function (biology); Robot; Artificial intelligence; Simple (philosophy); Representation (politics); Range (aeronautics); Bellman equation; Machine learning; Mathematics; Mathematical optimization","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004678765,0.0002949248,0.0003711738,0.0001270326,0.0002899366,0.0003165401,0.000781049,0.0004375414,0.001231341],"category_scores_gemma":[0.001232657,0.0002068455,0.0002674912,0.0001128631,0.0007006433,0.0007616926,0.0006653189,0.0008115782,0.0001884972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000444949,"about_ca_system_score_gemma":0.0003919224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002945343,"about_ca_topic_score_gemma":0.001758667,"domain_scores_codex":[0.9998549,0.00002666893,0.000006479821,0.00005070154,0.00003685458,0.0000244687],"domain_scores_gemma":[0.9996243,0.0001529876,0.00005326302,0.00006938379,0.00004072527,0.00005931802],"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":[0.0003029757,0.0001443582,0.002412208,0.00005085818,0.00002385299,0.0002662944,0.0001567911,0.9017844,0.03224989,0.01288744,0.0006275696,0.04909336],"study_design_scores_gemma":[0.00001245267,0.0000499442,0.0002524077,0.000001723638,0.000003106521,0.00002235386,0.000006127183,0.9944155,0.00197861,0.00296235,0.0002894161,0.000005982331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4115186,0.0001675445,0.5813028,0.0003775381,0.00007913138,0.00004779157,0.00005022481,0.001927065,0.004529418],"genre_scores_gemma":[0.9509375,0.0000321252,0.0476096,0.00003322187,0.000007346715,0.00002106513,0.00002309764,0.00002486675,0.001310993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002945343,"threshold_uncertainty_score":0.005856395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05642375213541702,"score_gpt":0.2814493595591195,"score_spread":0.2250256074237025,"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."}}