{"id":"W4409785434","doi":"10.61091/jcmcc127b-506","title":"Reinforcement learning-based state space dimensionality reduction and optimal control strategy design in robot navigation systems","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Dimensionality reduction; State space; Computer science; Reduction (mathematics); Control (management); State (computer science); Robot; Artificial intelligence; Curse of dimensionality; Space (punctuation); Robot learning; Control engineering; Control theory (sociology); Engineering; Mobile robot; Mathematics; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.003560127,0.0002715256,0.0006919187,0.0002939289,0.0002637414,0.0004667973,0.0003680461,0.0001276627,2.676446e-7],"category_scores_gemma":[0.0003478372,0.0002557829,0.0000827524,0.0004205335,0.00009021449,0.0003779308,0.000159224,0.0005827574,3.315282e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002309195,"about_ca_system_score_gemma":0.0003449443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003401441,"about_ca_topic_score_gemma":1.389255e-7,"domain_scores_codex":[0.9971902,0.0004654917,0.001143157,0.0002975784,0.000566541,0.000336984],"domain_scores_gemma":[0.9970151,0.0009326138,0.001102901,0.0002156621,0.0006048524,0.0001288937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001915473,0.0002322917,0.0000934748,0.0001500718,0.00008308632,0.00002836537,0.000341213,0.4382735,0.0005650498,0.5582407,0.00001302702,0.001787692],"study_design_scores_gemma":[0.006459918,0.0008727196,0.0001372895,0.0006072512,0.00004366026,0.00004926741,0.0001507128,0.8825507,0.0001883176,0.1087086,0.00003067278,0.0002008998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1274551,0.000344673,0.8669354,0.0002047165,0.004454619,0.0005319908,2.704859e-7,0.00004066935,0.00003258852],"genre_scores_gemma":[0.9865763,0.000009969123,0.01323008,0.000008348324,0.0001464434,0.00000606797,8.73515e-7,0.00001255695,0.000009329935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8591213,"threshold_uncertainty_score":0.9999894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01231466177598489,"score_gpt":0.2554469431974484,"score_spread":0.2431322814214635,"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."}}