{"id":"W4402036074","doi":"10.1016/j.eswa.2024.125238","title":"A deep residual reinforcement learning algorithm based on Soft Actor-Critic for autonomous navigation","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Residual; Artificial intelligence; Algorithm; Machine learning; Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0003736482,0.0002381762,0.0002164458,0.0001947242,0.0004139671,0.000498035,0.0005131496,0.0000944487,0.000002649977],"category_scores_gemma":[0.00002637193,0.0002055496,0.00006038101,0.0004870618,0.00004216854,0.0002840723,0.0000415829,0.0002150271,0.0001028583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002671561,"about_ca_system_score_gemma":0.0002487263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005864627,"about_ca_topic_score_gemma":4.656426e-7,"domain_scores_codex":[0.99804,0.00006815809,0.0003750561,0.0006833114,0.0004480819,0.0003854455],"domain_scores_gemma":[0.9984447,0.0004832454,0.0001033791,0.0006745338,0.0001496884,0.0001444988],"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":[0.00001202597,0.00009417638,0.00001470559,0.0002711801,0.00007338703,0.00002875551,0.002660513,0.8905368,0.0003465051,0.03070291,0.002954166,0.0723049],"study_design_scores_gemma":[0.0002801676,0.0002536459,0.00001028621,0.0003449023,0.00001077133,0.00003839359,0.000148933,0.951499,0.0001873965,0.00007474133,0.04689647,0.0002552239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000008351767,0.0006668125,0.9949586,0.0008100453,0.0003744336,0.001681994,0.000007579238,0.0009829074,0.0005092807],"genre_scores_gemma":[0.2620749,0.000005046735,0.720449,0.0002913718,0.0009657368,0.01400022,0.0003349989,0.00008671709,0.001791948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2745095,"threshold_uncertainty_score":0.8382071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574082428586497,"score_gpt":0.2779228990432605,"score_spread":0.2621820747573955,"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."}}