{"id":"W4384563452","doi":"10.1016/j.cogr.2023.07.004","title":"Reinforcement learning for swarm robotics: An overview of applications, algorithms and simulators","year":2023,"lang":"en","type":"article","venue":"Cognitive Robotics","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Swarm robotics; Reinforcement learning; Robotics; Robot; Swarm behaviour; Computer science; Swarm intelligence; Ant robotics; Machine learning; Field (mathematics); Popularity; Robot control; Mobile robot; Particle swarm optimization; 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":[0.0004597671,0.0001807351,0.0003109475,0.0001466847,0.000168036,0.00009480649,0.0003641202,0.00007740394,0.000001430259],"category_scores_gemma":[0.0001996642,0.0001878282,0.00007719061,0.000529961,0.00006448093,0.0002870976,0.0002084816,0.0001069548,0.00003074009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003780664,"about_ca_system_score_gemma":0.00005903486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008827477,"about_ca_topic_score_gemma":0.000001648954,"domain_scores_codex":[0.9984781,0.00008160727,0.0004171418,0.0004142661,0.0002769995,0.000331912],"domain_scores_gemma":[0.9983237,0.0005258138,0.0002484962,0.0003044906,0.000455054,0.0001424325],"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":[0.000009421577,0.00006709193,0.001014999,0.000249265,0.0001023632,0.000003299747,0.0003460361,0.9066827,0.0000979422,0.04223039,0.00004392651,0.04915261],"study_design_scores_gemma":[0.001026409,0.000203737,0.00124106,0.0001214678,0.00006003519,0.000002208179,0.0002883679,0.9949304,0.0003372644,0.00100202,0.0005679975,0.0002189806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004906963,0.0005655213,0.9972135,0.0001366416,0.0001446005,0.001128575,0.00001972249,0.0002178361,0.00008287533],"genre_scores_gemma":[0.9778429,0.0002761425,0.02095809,0.00009520668,0.000106898,0.0002207961,0.000214647,0.000028916,0.0002564465],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9773521,"threshold_uncertainty_score":0.765941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08144672949125539,"score_gpt":0.3443128008019918,"score_spread":0.2628660713107364,"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."}}