About PPO

[LpLegend]

I don't think this code can solve the problem(pendulum), and another question is why this reward is 'running_reward * 0.9 + score * 0.1'

[LpLegend]

I have changed the activate function from relu to tanh, but there is nothing improvement.

[heyfavour]

I don't think this code can solve the problem(pendulum), and another question is why this reward is 'running_reward * 0.9 + score * 0.1'

我也遇到这个问题，我咨询elegantrl作者，他说先tahn，再通过torch.distribution来sample action会影响信息熵，所以是没有办法收敛的，但是我不喜欢elegantrl的ppo写法，所以我还在找别人的代码

[CoulsonZhao]

Have you got the right code yet? Could you copy a link? Very appreciate!!

[huang-chunyang]

I don't think this code can solve the problem(pendulum), and another question is why this reward is 'running_reward * 0.9 + score * 0.1'

You can change clip_param from 0.2 into 0.1, constrainting trust regions. This method can work!