{"id":"W4400972116","doi":"10.2316/j.2024.206-1114","title":"OVERCOMING VALUE OVERESTIMATION FOR DISTRIBUTIONAL REINFORCEMENT LEARNING-BASED PATH PLANNING WITH CONSERVATIVE CONSTRAINTS","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":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Path (computing); Value (mathematics); Computer science; Mathematical optimization; Operations research; Artificial intelligence; Psychology; Mathematics; Machine learning; Social psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004616754,0.001231381,0.001820284,0.0007619046,0.0007144007,0.001367153,0.002811326,0.001622466,0.002980347],"category_scores_gemma":[0.02578195,0.0008491401,0.000500441,0.0007966943,0.001799162,0.002668094,0.003865355,0.003555665,0.0003439011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001583687,"about_ca_system_score_gemma":0.002223237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003472784,"about_ca_topic_score_gemma":0.003962125,"domain_scores_codex":[0.9974491,0.001105214,0.0001362727,0.0003641353,0.0006162614,0.0003289311],"domain_scores_gemma":[0.9783787,0.01739577,0.001131751,0.001036092,0.00145027,0.000607333],"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":[0.0003776458,0.0001306255,0.001266859,0.0001794963,0.00006518979,0.0001242357,0.0001862228,0.9139074,0.001525757,0.02155437,0.00168214,0.05900013],"study_design_scores_gemma":[0.00002448968,0.00004458199,0.00005853116,0.00001043563,0.000006306311,0.00001402663,0.00001151237,0.9860783,0.0002842374,0.013319,0.0001444724,0.000004099226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05563486,0.0003072146,0.9398764,0.0005497807,0.00008020586,0.0000837782,0.00006339182,0.000433104,0.00297131],"genre_scores_gemma":[0.9143569,0.0001135182,0.08299085,0.0002526969,0.00006385783,0.0001619275,0.000110482,0.0001589894,0.001790694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004616754,"threshold_uncertainty_score":0.02441603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01897315524903784,"score_gpt":0.2928042851376677,"score_spread":0.2738311298886298,"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."}}