{"id":"W4387725412","doi":"10.48550/arxiv.2310.10502","title":"Adaptive Robot Assistance: Expertise and Influence in Multi-User Task Planning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partially observable Markov decision process; Computer science; Heuristics; Task (project management); Scalability; Robot; Markov decision process; Unobservable; Artificial intelligence; Process (computing); Human–computer interaction; Domain (mathematical analysis); Machine learning; Markov process; Markov chain; Engineering; Markov model; Systems engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002863634,0.0003564268,0.0003677364,0.000426356,0.0001394476,0.0002220595,0.00147805,0.0003025824,0.00000258439],"category_scores_gemma":[0.0001363825,0.0004333848,0.00008376416,0.0007070743,0.000124535,0.000728338,0.002855933,0.0008907568,0.00005800809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003434377,"about_ca_system_score_gemma":0.0001505699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002728113,"about_ca_topic_score_gemma":0.00005213104,"domain_scores_codex":[0.9976927,0.0001461104,0.0002867912,0.001253069,0.000146668,0.0004746429],"domain_scores_gemma":[0.9982641,0.0001789736,0.0002889083,0.0009740792,0.0001343329,0.0001596169],"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":[0.00001978951,0.00001953321,0.04203915,0.00004022729,0.00003394136,0.0006584982,0.00115461,0.9473165,0.00003315956,0.008573049,0.00004045448,0.000071093],"study_design_scores_gemma":[0.0005684014,0.00004225034,0.06234811,0.0004145574,0.00001528035,0.000001679814,0.0002744471,0.9351373,0.00001951871,0.0006324197,0.00009275489,0.0004532668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1094489,0.00008438231,0.8892514,0.0000441319,0.0003846926,0.0002796519,0.000003104232,0.0003076708,0.0001961339],"genre_scores_gemma":[0.9853516,0.0001468612,0.010711,0.0000788922,0.00002032411,0.00000307574,0.000005523239,0.00002746636,0.003655216],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8785404,"threshold_uncertainty_score":0.9998118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1377794439627749,"score_gpt":0.2335253001864412,"score_spread":0.09574585622366635,"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."}}