{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001987535,0.0001217976,0.0001248481,0.00008642904,0.0001312404,0.00003587924,0.0001154816,0.00004631594,0.00006332248],"category_scores_gemma":[0.0003410119,0.0001149933,0.0000405446,0.0001892512,0.00004318887,0.0001707942,0.00007702277,0.0002589657,0.00009602871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005967633,"about_ca_system_score_gemma":0.000009937315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009204209,"about_ca_topic_score_gemma":0.00003750737,"domain_scores_codex":[0.9988776,0.0001192329,0.0002224281,0.0003377303,0.0001732431,0.0002697082],"domain_scores_gemma":[0.9995484,0.0001516114,0.00009410934,0.0001289927,0.00002005129,0.00005679274],"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":[0.00002656056,0.00009763331,0.005506251,0.000002535934,5.972488e-7,0.00001781067,0.0001323566,0.01578629,0.9522032,0.0008118264,0.00000778652,0.0254072],"study_design_scores_gemma":[0.00153987,0.0008317049,0.1167631,0.00005661967,0.0000230472,0.00002123655,0.0001584243,0.79825,0.07982334,0.00004647724,0.002023082,0.0004630388],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9791069,0.000003940159,0.01833713,0.00006600348,0.0002399762,0.0003356726,7.822419e-7,0.00008819569,0.001821404],"genre_scores_gemma":[0.9955667,0.000003416238,0.0009720213,0.0002261274,0.0000342639,0.00006742903,0.00000238151,0.00001749436,0.003110117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8723798,"threshold_uncertainty_score":0.468929,"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."}}