{"id":"W2963274839","doi":"","title":"Reinforcement Learning based Embodied Agents Modelling Human Users Through Interaction and Multi-Sensory Perception","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Task (project management); Reinforcement learning; Embodied cognition; Perception; Artificial intelligence; Control (management); Human–computer interaction; Complement (music); Feedback control; Machine learning; Control engineering; Engineering","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":[0.0007705381,0.0006080595,0.0004867245,0.0002300735,0.0002339089,0.0008476534,0.0009354544,0.0008406322,0.002358503],"category_scores_gemma":[0.003798954,0.0003812604,0.0004596066,0.0001834281,0.00107892,0.001060589,0.001028558,0.0009673785,0.0003069747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006453785,"about_ca_system_score_gemma":0.0005867681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003890781,"about_ca_topic_score_gemma":0.003006505,"domain_scores_codex":[0.9996117,0.0001876194,0.00001738284,0.00008132808,0.00005914989,0.00004293162],"domain_scores_gemma":[0.9983522,0.001019256,0.0002418491,0.0001628631,0.0001270447,0.00009693242],"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":[0.00009033621,0.00005975695,0.001056325,0.00003649335,0.00003141876,0.00009024329,0.0002428755,0.974317,0.003160305,0.009667816,0.0001314898,0.01111592],"study_design_scores_gemma":[0.000007423117,0.00003243336,0.0001171257,0.000002713725,0.000003932377,0.00001047378,0.00001080153,0.9963102,0.0003347693,0.002990994,0.0001743772,0.000004739833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1302726,0.0001351836,0.8647674,0.0003108945,0.00002952806,0.0000581608,0.00004670447,0.0003389576,0.004040597],"genre_scores_gemma":[0.9515628,0.00007525283,0.0453507,0.00003591219,0.000009525318,0.00006923993,0.00002048527,0.00002205635,0.002853988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003890781,"threshold_uncertainty_score":0.007889926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2039206130927987,"score_gpt":0.2604560799500727,"score_spread":0.05653546685727395,"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."}}