{"id":"W4395703972","doi":"10.2139/ssrn.4771123","title":"Autonomous Robot Navigation in Dynamic Environments: A Temporal-Difference Learning Approach","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Temporal difference learning; Computer science; Robot; Artificial intelligence; Human–computer interaction; Reinforcement learning","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":[0.001312315,0.000412473,0.0009480341,0.0003912525,0.0003647803,0.0006493887,0.002028143,0.001050386,0.001974709],"category_scores_gemma":[0.002595275,0.0004041094,0.0005518377,0.0005319359,0.00105943,0.001339388,0.0013355,0.001231043,0.0001725772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007805739,"about_ca_system_score_gemma":0.000975056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003997553,"about_ca_topic_score_gemma":0.002710998,"domain_scores_codex":[0.9996654,0.0001001301,0.00001922966,0.00008414702,0.00009225953,0.00003887193],"domain_scores_gemma":[0.9987722,0.0007900526,0.0001029919,0.00006314573,0.0001790171,0.0000925106],"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":[0.0001487564,0.000116808,0.0007114208,0.0000793081,0.00007320265,0.00005274017,0.00007248946,0.8822873,0.00237408,0.04934038,0.0005383631,0.06420524],"study_design_scores_gemma":[0.000005766437,0.0000217168,0.00003886849,0.000001682998,0.000003909216,0.000005964532,0.000001917778,0.9935449,0.0001122269,0.006170725,0.00008956902,0.000002708131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01514633,0.0001978548,0.983003,0.0001547796,0.00004632054,0.00001336775,0.00001367171,0.0000527179,0.001371996],"genre_scores_gemma":[0.8638048,0.0003035803,0.1315896,0.0001340868,0.00008646956,0.0000992172,0.00005694816,0.00005253259,0.003872779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003997553,"threshold_uncertainty_score":0.007948577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007485515225629387,"score_gpt":0.2333386996151577,"score_spread":0.2258531843895283,"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."}}