公开(公告)号：US20220231933A1

公开(公告)日：2022-07-21

申请号：US17341210

申请日：2021-06-07

Applicant: NVIDIA Corporation

Inventor： Shie Mannor ,  Chen Tessler ,  Yuval Shpigelman ,  Amit Mandelbaum ,  Gal Dalal ,  Doron Kazakov ,  Benjamin Fuhrer

IPC: H04L12/26 ,  H04L12/803 ,  G06K9/62 ,  G06N3/08

Abstract: A reinforcement learning agent learns a congestion control policy using a deep neural network and a distributed training component. The training component enables the agent to interact with a vast set of environments in parallel. These environments simulate real world benchmarks and real hardware. During a learning process, the agent learns how maximize an objective function. A simulator may enable parallel interaction with various scenarios. As the trained agent encounters a diverse set of problems it is more likely to generalize well to new and unseen environments. In addition, an operating point can be selected during training which may enable configuration of the required behavior of the agent.

公开(公告)号：US20230041242A1

公开(公告)日：2023-02-09

申请号：US17959042

申请日：2022-10-03

Applicant: NVIDIA Corporation

Inventor： Shie Mannor ,  Chen Tessler ,  Yuval Shpigelman ,  Amit Mandelbaum ,  Gal Dalal ,  Doron Kazakov ,  Benjamin Fuhrer

IPC: H04L43/0817 ,  H04L43/067 ,  H04L43/0852 ,  G06N3/08 ,  H04L47/122 ,  G06K9/62 ,  H04L43/0882

Abstract: A reinforcement learning agent learns a congestion control policy using a deep neural network and a distributed training component. The training component enables the agent to interact with a vast set of environments in parallel. These environments simulate real world benchmarks and real hardware. During a learning process, the agent learns how maximize an objective function. A simulator may enable parallel interaction with various scenarios. As the trained agent encounters a diverse set of problems it is more likely to generalize well to new and unseen environments. In addition, an operating point can be selected during training which may enable configuration of the required behavior of the agent.