{"id":"W4285045354","doi":"10.20517/ir.2022.11","title":"AVDDPG – Federated reinforcement learning applied to autonomous platoon control","year":2022,"lang":"en","type":"article","venue":"Intelligence & Robotics","topic":"Traffic control and management","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Platoon; Reinforcement learning; Reinforcement; Computer science; Materials science; Control (management); Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002044495,0.0002097293,0.000233568,0.0001295102,0.0002865464,0.00008236137,0.0002644762,0.00003488972,0.000468484],"category_scores_gemma":[0.00001525429,0.0002392779,0.00006031995,0.0002605299,0.00001380569,0.00004038536,0.0001301983,0.0003644181,0.0002588411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002789683,"about_ca_system_score_gemma":0.00002445893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001666632,"about_ca_topic_score_gemma":0.00001820143,"domain_scores_codex":[0.9986433,0.00002117243,0.0003661366,0.0002391203,0.0002955098,0.000434806],"domain_scores_gemma":[0.9995524,0.00005446963,0.00003998858,0.0001972943,0.00002921731,0.0001266331],"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":[0.00003209425,0.00002082695,0.0000108045,0.00001557188,0.00006901083,0.00001503671,0.0004830718,0.943844,0.0005144179,0.005580082,0.0009779307,0.0484372],"study_design_scores_gemma":[0.0002553708,0.0001703465,0.00006425235,0.000006845216,0.00003533537,0.000004421838,0.0007648158,0.9315225,0.0004677063,0.00007814581,0.06629538,0.0003348985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00230305,0.000122108,0.9822035,0.0002453218,0.0007945226,0.000704731,0.000003108432,0.0008969472,0.01272672],"genre_scores_gemma":[0.9971564,0.00001395507,0.0007983451,0.0004406182,0.00006422152,0.0001930785,0.00001588248,0.00004212502,0.001275314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9948534,"threshold_uncertainty_score":0.9757468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024857588274035,"score_gpt":0.2051875602226315,"score_spread":0.1949389843398912,"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."}}