zhangchuheng123/Reinforcement-Implementation

Issues

• Issues regarding PPO implementation

  #3 opened 4 years ago by vwxyzjn
  1

• ppo中的loss_entropy方向应为最大化

  #2 opened 5 years ago by tangzk
  2

• About the line-search in TRPO

  #1 opened 6 years ago by ChenShawn
  0