{"id":"W4405603119","doi":"10.2316/j.2025.206-1114","title":"OVERCOMING VALUE OVERESTIMATION FOR DISTRIBUTIONAL REINFORCEMENT LEARNING-BASED PATH PLANNING WITH CONSERVATIVE CONSTRAINTS, 124-132.","year":2024,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Path (computing); Computer science; Mathematical optimization; Motion planning; Value (mathematics); Artificial intelligence; Mathematics; Machine learning; Engineering; Structural engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0005310319,0.0001263275,0.0001501103,0.0002044696,0.000104328,0.0004478703,0.0002448469,0.0000483698,0.00000359964],"category_scores_gemma":[0.0002176558,0.0001050518,0.00005112528,0.0001146216,0.00006575393,0.0006793597,0.00003671006,0.0001842528,0.000001312325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00016969,"about_ca_system_score_gemma":0.0003046326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002964901,"about_ca_topic_score_gemma":6.259481e-8,"domain_scores_codex":[0.9986862,0.00004297022,0.0004170529,0.0001629681,0.0005567305,0.0001340967],"domain_scores_gemma":[0.9984584,0.0005203752,0.0003667157,0.00006320848,0.0005275303,0.00006376888],"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":[0.00002812261,0.00001888795,0.0007496745,0.00003198949,0.0001143847,0.00006119389,0.0002881399,0.9275888,0.0001622084,0.06649879,0.0002078146,0.004250012],"study_design_scores_gemma":[0.0007210589,0.0003180893,0.003216037,0.0009464952,0.00002684884,0.0002446124,0.00003671896,0.9916397,0.0002419034,0.002121355,0.0003653697,0.0001218022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00397897,0.0001230481,0.9927024,0.002260144,0.0006844731,0.00012143,0.00001334192,0.00006247007,0.00005368937],"genre_scores_gemma":[0.7125174,0.000004619792,0.2871881,0.00009408245,0.0001130075,0.000003986271,0.00005453003,0.000006698702,0.00001761867],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7085384,"threshold_uncertainty_score":0.4318824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01889957237805722,"score_gpt":0.29031087367882,"score_spread":0.2714113013007628,"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."}}