{"id":"W3202938653","doi":"10.1109/lra.2022.3224667","title":"Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Reinforcement learning; Computer science; Robot; Robustness (evolution); Scalability; Artificial intelligence; Benchmark (surveying); Action selection; Macro; Computation; Machine learning; Distributed computing","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":[0.0008347955,0.0005455974,0.00066942,0.0001914176,0.0002847986,0.0004310224,0.001050107,0.0005345927,0.0009473379],"category_scores_gemma":[0.002218404,0.0003168438,0.0002584644,0.0001630615,0.0006465199,0.0007219228,0.0009985418,0.00120973,0.0001685512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008875368,"about_ca_system_score_gemma":0.001081637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004721893,"about_ca_topic_score_gemma":0.00537821,"domain_scores_codex":[0.9997658,0.000071248,0.0000105251,0.00005376384,0.00005305635,0.00004568382],"domain_scores_gemma":[0.9992326,0.0003834159,0.0001041945,0.00008833093,0.0001169928,0.00007437515],"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":[0.00006699478,0.00005997202,0.0008554871,0.00003099942,0.00002511766,0.00004645969,0.0000415645,0.9569575,0.001983753,0.003060345,0.0005906766,0.03628113],"study_design_scores_gemma":[0.000003921073,0.00001476954,0.00004987087,0.000001273998,0.00000126131,0.000003084646,0.000002639314,0.9985402,0.0002228019,0.001072606,0.00008632385,0.000001193082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06866162,0.0002660106,0.9283103,0.0002208376,0.00004757096,0.00004276851,0.0000413388,0.0006966105,0.001712919],"genre_scores_gemma":[0.9477465,0.00006324765,0.05047798,0.00008187461,0.00001484727,0.00006968065,0.00006717477,0.00003605317,0.001442788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004721893,"threshold_uncertainty_score":0.009388804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03577697130002772,"score_gpt":0.2664115826447513,"score_spread":0.2306346113447236,"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."}}