{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003018786,0.0001992014,0.0002508546,0.0003293178,0.000138817,0.0001159921,0.0001241851,0.00008677556,0.00003715273],"category_scores_gemma":[0.00002778706,0.0002096783,0.00009369998,0.0003735629,0.00001671914,0.0001216541,0.000003093576,0.0002271426,0.000320688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000092323,"about_ca_system_score_gemma":0.000009494387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005130035,"about_ca_topic_score_gemma":0.000001937729,"domain_scores_codex":[0.998665,0.0001118214,0.0003712048,0.0001927665,0.0002938217,0.0003653459],"domain_scores_gemma":[0.9994891,0.0001067219,0.00008851966,0.0001921015,0.00003373777,0.00008979432],"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":[0.00001273269,0.000002107251,0.0004854242,0.00007823294,0.00006318028,0.0000177537,0.0001104525,0.9789327,0.008653376,0.00002247517,0.01158326,0.00003831483],"study_design_scores_gemma":[0.001175772,0.00002538289,0.0003796405,0.000065318,0.00002047442,0.000002453015,0.00005577787,0.9920853,0.00004294408,3.149499e-7,0.005916643,0.0002299562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00928473,0.00009600562,0.9847153,0.0007536011,0.002233169,0.0004675308,0.000001094192,0.001771296,0.0006772458],"genre_scores_gemma":[0.9985717,0.000006722725,0.00004864298,0.0004930911,0.0003534759,0.00008060345,0.00006492245,0.00006148227,0.0003193466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.989287,"threshold_uncertainty_score":0.8550433,"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."}}