{"id":"W7124317253","doi":"10.65109/gzci2494","title":"Value Iteration for Learning Concurrently Executable Robotic Control Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Executable; Task (project management); Reinforcement learning; Set (abstract data type); Independence (probability theory); Robot; Property (philosophy); Control (management)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001228879,0.0005571746,0.0007308047,0.0004545783,0.001050693,0.002288779,0.001277159,0.0003023735,0.0001835521],"category_scores_gemma":[0.001059614,0.0005892897,0.0003385253,0.001000632,0.0001493845,0.001450771,0.0003905916,0.000722104,0.0002145283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002898781,"about_ca_system_score_gemma":0.000630051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004351444,"about_ca_topic_score_gemma":0.000002145302,"domain_scores_codex":[0.9956828,0.0003065715,0.001200778,0.001086256,0.0005822751,0.001141283],"domain_scores_gemma":[0.9966937,0.001086571,0.0005181782,0.0008449538,0.0007004966,0.0001561183],"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":[0.00003615133,0.00004815766,0.0008173174,0.0002150604,0.0001349955,0.00000185186,0.0002494832,0.7448843,0.0002673648,0.2405941,0.003153094,0.009598149],"study_design_scores_gemma":[0.00335079,0.0005276082,0.0001761756,0.0003423116,0.0002120386,0.000003706362,0.00006983667,0.9539949,0.0004759596,0.0009990213,0.03932269,0.0005250103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005549626,0.0007430037,0.9703804,0.002630098,0.005445203,0.001974064,0.000002179695,0.0003259601,0.01844363],"genre_scores_gemma":[0.8739147,0.00005911373,0.03322142,0.002611367,0.0002796848,0.0001385554,0.0000354698,0.0000373544,0.08970235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9371589,"threshold_uncertainty_score":0.9996558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01369195286495529,"score_gpt":0.2791122585949014,"score_spread":0.2654203057299461,"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."}}