{"id":"W2159008857","doi":"","title":"Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"octopus (software); Gaussian process; Robotic arm; Reinforcement learning; Temporal difference learning; Computer science; Artificial intelligence; Process (computing); Domain (mathematical analysis); Bayesian optimization; Bayesian probability; State space; Trajectory; Machine learning; Computer vision; Gaussian; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007647283,0.0003056866,0.0003412709,0.0003061249,0.0004690663,0.002099717,0.0009455087,0.0001014065,0.000003811785],"category_scores_gemma":[0.0001206369,0.0002357616,0.00003447767,0.0007447276,0.00004275696,0.00714332,0.00007197191,0.000409253,0.00006452866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119151,"about_ca_system_score_gemma":0.0001716455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003021276,"about_ca_topic_score_gemma":0.000002809947,"domain_scores_codex":[0.9974496,0.0002220586,0.000782695,0.000317184,0.0007189612,0.0005094458],"domain_scores_gemma":[0.9981142,0.00006351039,0.0006660353,0.000412675,0.0004625477,0.0002810446],"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":[0.00002128273,0.00001652988,0.001275458,0.0001808963,0.00000758873,0.000001139311,0.007293384,0.8867991,0.0001062164,0.0005555853,0.00001897975,0.1037239],"study_design_scores_gemma":[0.0005886306,0.0006137023,0.0007643517,0.0001670066,0.000008962836,0.00008004194,0.000898967,0.9928893,0.0004335642,0.000008906447,0.003192978,0.000353557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02859114,0.00003006504,0.9676716,0.000600391,0.0002500227,0.0005865825,7.580139e-7,0.0006732757,0.001596166],"genre_scores_gemma":[0.9461588,5.590228e-7,0.05237215,0.0007577442,0.0001347629,0.00009679658,0.0000148356,0.00001683829,0.0004475728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9175676,"threshold_uncertainty_score":0.9989362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02016052612471637,"score_gpt":0.3137583755310238,"score_spread":0.2935978494063075,"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."}}