{"id":"W7131116789","doi":"10.1109/robio66223.2025.11378377","title":"A Strategy Adaptive Adjustment Deep Reinforcement Learning Method with Behavior Cloning for Mobile Robot Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Reinforcement learning; Obstacle avoidance; Randomness; Obstacle; Robot; Mobile robot; Trajectory; Training (meteorology); Path (computing)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001581939,0.0009317533,0.0008789406,0.0004960418,0.001202881,0.0009258385,0.001298592,0.0003676337,0.0001984614],"category_scores_gemma":[0.00009172258,0.00086592,0.0003339518,0.001491395,0.0001794407,0.001276203,0.0007321863,0.001069056,0.00004313538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009665174,"about_ca_system_score_gemma":0.0008620241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002361204,"about_ca_topic_score_gemma":0.00002126005,"domain_scores_codex":[0.9937375,0.0004483699,0.001553417,0.001649577,0.001123942,0.001487199],"domain_scores_gemma":[0.9957654,0.0007485978,0.001006598,0.001128889,0.001048138,0.0003023575],"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":[0.0002308414,0.0001302259,0.000232091,0.0001895781,0.0003381257,0.00001293464,0.001531578,0.8332508,0.0003585125,0.04097883,0.0000528382,0.1226937],"study_design_scores_gemma":[0.002846015,0.00771788,0.0005673502,0.0007864141,0.0006787343,0.00002010094,0.002929436,0.978405,0.003921974,0.0001169987,0.001089024,0.0009210923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005715542,0.0005793757,0.984071,0.0001099372,0.0009664298,0.005993002,0.000001216817,0.0003512793,0.007356217],"genre_scores_gemma":[0.542633,0.00005897895,0.4305947,0.0002261168,0.000114318,0.0023318,0.00008456765,0.00005846466,0.02389802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5534762,"threshold_uncertainty_score":0.9993792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0254119146095384,"score_gpt":0.3187286794351319,"score_spread":0.2933167648255935,"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."}}