{"id":"W4389459373","doi":"10.1109/lcsys.2023.3340619","title":"RL-PGO: Reinforcement Learning-Based Planar Pose-Graph Optimization","year":2023,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Solver; Markov decision process; Computer science; Graph; Artificial intelligence; Observable; Mathematical optimization; Partially observable Markov decision process; Nonlinear system; Machine learning; Algorithm; Markov chain; Theoretical computer science; Markov process; Mathematics; Markov model","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":[0.0006148776,0.001088269,0.001031696,0.0003172764,0.0002858014,0.0006419956,0.001674857,0.00124387,0.004371178],"category_scores_gemma":[0.002491419,0.0004970429,0.0005126162,0.0003477964,0.0008927934,0.0008233081,0.001771664,0.00167032,0.0009757306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000584612,"about_ca_system_score_gemma":0.001337455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004516082,"about_ca_topic_score_gemma":0.005672175,"domain_scores_codex":[0.999668,0.00009280495,0.00001178357,0.00009509931,0.00008231352,0.00004998007],"domain_scores_gemma":[0.9992927,0.0004244092,0.0000709579,0.00008092788,0.00007493283,0.00005603786],"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":[0.00005794975,0.00004461994,0.0003872311,0.00006638429,0.00002941832,0.00005692583,0.00002784193,0.9271807,0.001177723,0.006515677,0.0024897,0.06196582],"study_design_scores_gemma":[0.000007279024,0.00001393061,0.00002013529,0.000002743618,0.000001810019,0.000006826367,0.000002177261,0.9977665,0.0001778653,0.001646149,0.0003528919,0.000001803529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007709088,0.0002256008,0.9874549,0.0001974912,0.00005878019,0.00005632338,0.0000791302,0.001424217,0.00279453],"genre_scores_gemma":[0.5734141,0.0002638754,0.4175935,0.000600536,0.00008460829,0.0003110076,0.0005461962,0.0004749741,0.006711086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004516082,"threshold_uncertainty_score":0.01462299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244377195448505,"score_gpt":0.2020894477977216,"score_spread":0.1896456758432365,"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."}}