{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000259682,0.0001772599,0.0001625545,0.000169635,0.0009911851,0.0002962599,0.0002846015,0.00002964897,0.00001421464],"category_scores_gemma":[0.00002754056,0.0001786979,0.00005273235,0.000304629,0.00003721644,0.0007348805,0.0001017126,0.0002181485,0.000005468016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001558438,"about_ca_system_score_gemma":0.00003903545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008203789,"about_ca_topic_score_gemma":0.000002912356,"domain_scores_codex":[0.9985303,0.0000930653,0.000325136,0.000323024,0.0003983619,0.0003301202],"domain_scores_gemma":[0.9991977,0.000108872,0.0002838777,0.0002554156,0.00007300006,0.0000811978],"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":[0.00001239814,0.00001914818,0.000149878,0.00002234129,0.00003440208,0.000002609048,0.0009966803,0.9915832,0.002753324,0.002978636,0.0002120618,0.001235324],"study_design_scores_gemma":[0.001192295,0.0002339474,0.0002767893,0.00001269472,0.00002460875,0.00001419829,0.0001488856,0.9957434,0.000338297,0.00002352818,0.001754048,0.0002373348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001488518,0.00001372297,0.9924181,0.004737666,0.0004706758,0.0005614795,3.68764e-7,0.0002874356,0.00002200619],"genre_scores_gemma":[0.7050973,0.0000256007,0.2930408,0.001175998,0.00004220693,0.0002356307,0.00005988253,0.00002733386,0.0002952317],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7036088,"threshold_uncertainty_score":0.7623495,"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."}}