{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002026258,0.0001921493,0.0001595751,0.0001239619,0.001347773,0.0003497535,0.0006951614,0.00009211888,0.00003282833],"category_scores_gemma":[0.00003594446,0.00022799,0.00007890808,0.00008863089,0.0001151663,0.001831589,0.0003582477,0.0003168987,0.00005588527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001870432,"about_ca_system_score_gemma":0.00002327849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002651564,"about_ca_topic_score_gemma":0.0000114901,"domain_scores_codex":[0.9987807,0.00008735219,0.0001806517,0.0005396843,0.0001158838,0.0002957754],"domain_scores_gemma":[0.9986936,0.00004219769,0.000343984,0.0007320257,0.00009272504,0.00009547152],"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":[0.00001521445,0.00001672195,0.005866436,0.00001691239,0.00002232924,0.00002727609,0.0006227537,0.9861292,0.0002272895,0.006915675,0.00001474523,0.000125445],"study_design_scores_gemma":[0.0009735622,0.00009833418,0.002290343,0.00005260028,0.0000250965,0.000001548179,0.0003176731,0.9954831,0.00008317886,0.0001252566,0.0003045203,0.0002448016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1960934,0.000001473426,0.8003227,0.00003668237,0.0001676981,0.0001344471,1.526447e-7,0.000130706,0.003112705],"genre_scores_gemma":[0.9877468,0.00004080411,0.00822708,0.00007912085,0.00002696522,4.951473e-7,0.00000716555,0.00001382224,0.003857801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7920957,"threshold_uncertainty_score":0.9999523,"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."}}