{"id":"W4394944255","doi":"10.3390/robotics13040063","title":"Safe Reinforcement Learning for Arm Manipulation with Constrained Markov Decision Process","year":2024,"lang":"en","type":"article","venue":"Robotics","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Markov decision process; Process (computing); Computer science; Partially observable Markov decision process; Artificial intelligence; Markov chain; Reinforcement; Markov process; Machine learning; Engineering; Markov model; Mathematics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001311989,0.0001395431,0.0001225628,0.0001130639,0.00009366625,0.0001171004,0.00005668639,0.00006537826,0.0001073146],"category_scores_gemma":[0.00003913603,0.0001255109,0.00003980216,0.0001900551,0.00001401332,0.0001511433,0.000008024936,0.0001854033,0.00003643684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007004185,"about_ca_system_score_gemma":0.00002436347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.687136e-7,"about_ca_topic_score_gemma":0.000003342598,"domain_scores_codex":[0.9992403,0.000008207705,0.0002192093,0.0001566142,0.0001767079,0.0001989811],"domain_scores_gemma":[0.9996527,0.0001255712,0.00002455453,0.00008957163,0.00005403809,0.00005351465],"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":[0.00002074776,0.000004127791,0.0002217121,0.0002418256,0.00003112065,0.000004614172,0.0002266627,0.9815685,0.00006729881,0.003114255,0.0001535416,0.01434559],"study_design_scores_gemma":[0.0002920695,0.00008894887,0.0003242284,0.0002271192,0.0000315238,0.00001139977,0.0001060892,0.9955435,0.0001033596,0.0002071823,0.002887097,0.0001774158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00286359,0.0001184989,0.9906521,0.00007273181,0.0002905336,0.0002941474,1.774695e-7,0.0005021122,0.005206096],"genre_scores_gemma":[0.9769191,0.00001543445,0.02196634,0.00001808104,0.000116606,0.0000195295,0.00005741424,0.00005303375,0.0008344231],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740555,"threshold_uncertainty_score":0.5118188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01842831946777056,"score_gpt":0.2610140964488706,"score_spread":0.2425857769811001,"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."}}