{"id":"W4308531274","doi":"10.3390/electronics11213628","title":"Efficient Deep Reinforcement Learning for Optimal Path Planning","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Motion planning; Path (computing); Artificial neural network; Artificial intelligence; Process (computing); Dynamic programming; Mobile robot; Robot; Position (finance); Machine learning; Mathematical optimization; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006075924,0.0001101666,0.0001107518,0.00007445625,0.0008416852,0.00007427481,0.0005379988,0.00002021918,0.00003351328],"category_scores_gemma":[0.00004765133,0.0001165668,0.00007148072,0.0002289889,0.000007483363,0.00003464881,0.0003351431,0.0003944058,0.000008384783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001920919,"about_ca_system_score_gemma":0.0001150226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002921405,"about_ca_topic_score_gemma":1.803155e-7,"domain_scores_codex":[0.9986234,0.00007583679,0.0001572536,0.0002971433,0.0003021376,0.0005442782],"domain_scores_gemma":[0.9995079,0.00008294436,0.00009324934,0.0002352546,0.00002555311,0.00005509353],"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":[0.00001522261,0.00002411844,0.00005204524,0.00000533166,0.00001063414,0.00000355232,0.00114362,0.9629576,0.00008279382,0.01596674,0.0005615592,0.01917681],"study_design_scores_gemma":[0.0002815159,0.000573435,0.0000241936,0.000002145587,0.000003360269,0.00001258043,0.00005501785,0.7457001,0.00008008505,0.00009486517,0.2530599,0.0001128682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04168959,0.001739174,0.9544922,0.000382474,0.0001959676,0.0001678019,1.593632e-7,0.0002248059,0.001107874],"genre_scores_gemma":[0.9876894,0.000006856915,0.01033559,0.0002457474,0.00005953398,0.0001082563,0.00001430135,0.00001522858,0.001525078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9459998,"threshold_uncertainty_score":0.6473647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008262987290518933,"score_gpt":0.2469505914624998,"score_spread":0.2386876041719808,"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."}}