wangyuxiang8/rl-demo

强化学习常见算法的实现，Q-Learning/DQN/PG/AC/DDPG/PPO/SAC

RL-demo

强化学习常见算法的实现，Q-Learning/DQN/PG/AC/DDPG/PPO/SAC

rl-demo's Issues

PPO Actor Loss

You have done a very nice work! I have some questions to ask you...
In the RL-demo/PPO/agent.py folder, I see the loss function in the 70th line. I think the function, that you have written, should be ppo_actor's objective function, which is expected to be larger. However, ppo_actor's loss should be smaller... So, is a minus sign missing here? Or, is my understanding of PPO not deep enough? Expect your answer!

The following is a Chinese translation.
大佬你好，我观察到在你RL-demo/PPO/agent.py的第70行里面出现了PPO_actor的loss公式，但是我觉得那个应该是PPO_actor的目标函数，即一个越大越好的指标，Loss应该是越小越好的。所以这里是不是缺了一个负号？还是我对公式的理解不够透彻？希望您不吝赐教。