{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006472406,0.0007465435,0.0007084946,0.0003647089,0.0004232544,0.0005209754,0.001330228,0.0008819262,0.001232194],"category_scores_gemma":[0.001440467,0.0004662519,0.0005160519,0.0002928539,0.0009519201,0.0007372603,0.001203701,0.001158171,0.0002226878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009288237,"about_ca_system_score_gemma":0.001292726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01077933,"about_ca_topic_score_gemma":0.01030187,"domain_scores_codex":[0.9997442,0.00005645974,0.00001278391,0.00006368568,0.00007057986,0.00005228404],"domain_scores_gemma":[0.9994692,0.0002626759,0.00007474264,0.00005695585,0.00007806733,0.00005836093],"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":[0.00002645981,0.00002811102,0.0004121212,0.00001980405,0.00001953277,0.0000406523,0.00002924166,0.9666756,0.001062477,0.003832378,0.000407261,0.02744645],"study_design_scores_gemma":[0.000003983118,0.000007266714,0.00002308901,0.000001265779,0.000001336392,0.000003752167,0.000001888409,0.9987271,0.0001357472,0.0009777211,0.0001154949,0.000001196233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01833064,0.0001259429,0.9791899,0.0001502364,0.00002766729,0.00002941353,0.00001634849,0.0004786364,0.001651326],"genre_scores_gemma":[0.8114507,0.0001311209,0.1854056,0.0001569814,0.00002809373,0.0001264629,0.00007588108,0.00006181426,0.002563323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01077933,"threshold_uncertainty_score":0.02143317,"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."}}