Skip to main content

1 Result(s)

within Wu Qingtao Remove this filter Computer Science Remove this filter Mechanical Engineering Remove this filter

and

  1. No Access

    Article

    Decentralized multi-task reinforcement learning policy gradient method with momentum over networks

    To find the optimal policy quickly for reinforcement learning problems, policy gradient (PG) method is very effective, it parameters the policy and updates policy parameter directly. Besides, momentum methods ...

    Shi Junru, Wang Qiong, Liu Muhua, Ji Zhihang, Zheng Ruijuan… in Applied Intelligence (2023)