{"id":"W4297848563","doi":"10.48550/arxiv.2001.06627","title":"Multi-agent Motion Planning for Dense and Dynamic Environments via Deep\\n Reinforcement Learning","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Motion planning; Mathematical optimization; Artificial intelligence; Collision; Path (computing); Simple (philosophy); Algorithm; Mathematics; Robot","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006330339,0.0009939821,0.0008100721,0.0004214378,0.001073105,0.0004087137,0.001675026,0.000578368,0.00005018304],"category_scores_gemma":[0.0002343899,0.001327007,0.0004096551,0.0004880057,0.0003080379,0.0008090406,0.003932336,0.001526383,0.0001751123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001093314,"about_ca_system_score_gemma":0.0001224227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003839175,"about_ca_topic_score_gemma":0.000004004645,"domain_scores_codex":[0.9946588,0.0003550789,0.0008426977,0.002685486,0.0003523841,0.001105543],"domain_scores_gemma":[0.9964408,0.0003039076,0.001292425,0.001167633,0.0001530221,0.0006422664],"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":[0.0001565633,0.00006929905,0.003228704,0.0003432651,0.0003639061,0.0002114735,0.002465547,0.9895827,0.0008129154,0.001099691,0.00001034715,0.001655563],"study_design_scores_gemma":[0.002599574,0.0006107304,0.002971978,0.0002854501,0.000388184,0.00001336665,0.0004983647,0.9899029,0.0001126031,0.0003201723,0.001125565,0.001171138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02062064,0.0001206459,0.976119,0.0001383944,0.0008911431,0.001782977,0.000002913515,0.000197712,0.0001265341],"genre_scores_gemma":[0.9759098,0.0007163786,0.01759277,0.0001957481,0.00007378008,0.000008302699,0.0001298019,0.00008597682,0.005287438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9585263,"threshold_uncertainty_score":0.9989179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0764126386328068,"score_gpt":0.2122913612488068,"score_spread":0.135878722616,"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."}}