{"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":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001603407,0.0002124191,0.0001852823,0.0002799282,0.000178096,0.0004497235,0.0008049934,0.00009845242,0.000005562272],"category_scores_gemma":[0.00003875104,0.000198524,0.00008942961,0.0004854229,0.00004099096,0.000674403,0.000149631,0.003526578,0.00008274517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002251383,"about_ca_system_score_gemma":0.001031048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002690631,"about_ca_topic_score_gemma":0.00001401723,"domain_scores_codex":[0.9968431,0.0001774453,0.0004239485,0.000421868,0.0004374212,0.00169623],"domain_scores_gemma":[0.9994544,0.00005661418,0.0001452847,0.0002539368,0.00001530735,0.00007448324],"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":[0.000004633348,0.00003726958,0.001344585,0.00002149938,0.0000566752,0.00002680593,0.0007958225,0.8746239,0.000843854,0.06399391,0.000002923879,0.05824814],"study_design_scores_gemma":[0.0002571188,0.0002361659,0.0009614211,0.00008734901,0.000008981026,0.0005058367,0.0002436643,0.9793207,0.0000207384,0.01729986,0.0008294879,0.0002286969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02064252,0.001583714,0.9763583,0.0004061545,0.0002387955,0.0001391116,1.162232e-7,0.0001467674,0.0004845402],"genre_scores_gemma":[0.9857172,0.0008065456,0.006864315,0.00002466046,0.00005466268,0.00001124779,0.00001196636,0.00002576236,0.006483574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.969494,"threshold_uncertainty_score":0.9987723,"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."}}