{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008676758,0.0007812529,0.0009901503,0.0003925541,0.0003336797,0.0004946605,0.001288611,0.0008437427,0.002083358],"category_scores_gemma":[0.002712663,0.0005731966,0.000386168,0.0003561282,0.0007412537,0.0009680732,0.0009484189,0.001604337,0.0003010443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009540856,"about_ca_system_score_gemma":0.001358175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005173397,"about_ca_topic_score_gemma":0.004913885,"domain_scores_codex":[0.9996208,0.0001038523,0.00002125108,0.0000880896,0.0001056066,0.00006048007],"domain_scores_gemma":[0.9990659,0.0005368961,0.00009582071,0.00006855034,0.0001773728,0.00005548623],"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":[0.00003926587,0.00003190418,0.0003378211,0.00005244952,0.00001728873,0.00004259755,0.00003523935,0.9487571,0.001388568,0.005408728,0.0006614373,0.04322764],"study_design_scores_gemma":[0.00000404235,0.000008467842,0.00001841539,0.00000227053,0.000001125879,0.000004039513,0.000001680737,0.9983493,0.0002068389,0.001257175,0.0001451105,0.000001515375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007011022,0.000124329,0.9915966,0.00009728337,0.00001995037,0.0000209073,0.00002010953,0.0003088202,0.0008009679],"genre_scores_gemma":[0.697174,0.0001749902,0.2990947,0.0001954288,0.0000379173,0.0002344605,0.0001621831,0.0001321911,0.002794199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005173397,"threshold_uncertainty_score":0.01028657,"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."}}