{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001248341,0.000428539,0.0005653368,0.0002421652,0.0002756261,0.0005227871,0.0005831323,0.0007515373,0.0009799373],"category_scores_gemma":[0.002968915,0.0002858739,0.0003760848,0.0002330721,0.0007122848,0.0004964898,0.0006865066,0.0009550925,0.0001240978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007421789,"about_ca_system_score_gemma":0.0009401019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008213351,"about_ca_topic_score_gemma":0.004601019,"domain_scores_codex":[0.9997544,0.00008929439,0.00001521902,0.00004316212,0.00006688849,0.00003105334],"domain_scores_gemma":[0.9987156,0.0009008456,0.0001332468,0.00004799545,0.0001512262,0.00005109732],"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":[0.00005754593,0.00003420778,0.0002554324,0.00002106418,0.00001626607,0.00002365763,0.00004016124,0.9739476,0.001106539,0.005065539,0.0002019837,0.01922991],"study_design_scores_gemma":[0.000004828745,0.000009906638,0.00001553211,8.678791e-7,0.00000109676,0.000001544579,8.879275e-7,0.9991431,0.0001373734,0.000635331,0.00004822995,0.000001282505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04019265,0.0001199111,0.9576647,0.0002162679,0.00003013316,0.00003405509,0.00001204543,0.0001935997,0.001536557],"genre_scores_gemma":[0.8975414,0.00008964018,0.1000891,0.0001051017,0.0000173276,0.0001030268,0.00002842933,0.00002519619,0.002000662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008213351,"threshold_uncertainty_score":0.01633108,"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."}}