-
I'm trying to remove `kwargs` out of all the algorithms. In ERWR the default `positive_adv` is set to True. When it passing to VPG, then NPO, the `self.positive_adv` is never set, so [line 279](https:…
-
Need to be able to utilize the module to create a VPG.
-
I noticed that when I use the interpolation equation
theta_new = theta_old + alpha*(theta_new-theta_old)
where theta are the parameters of the policy network
When i set the value of alpha eq…
-
Hi, a quick question. Is there a way to set random seed in tensorforce? Thanks!
-
**URL**: https://www.cbs.com/shows/ncis-new-orleans/video/_M_unbWqoe2MMitcFWiWGDX38MXNt44o/ncis-new-orleans-in-plain-sight/
**Browser / Version**: Firefox 67.0
**Operating System**: Windows 8.1
*…
-
Dear developers,
I am using tensorforce 0.5.0. I use folowing code to restore a PPO model, but failed.
```
restore_directory = './saver_data/'
restore_file = 'model-32000'
agent.restore(resto…
-
while running main.py, after some training steps, I got the ｅｒｒｏｒ described in title. IndexError: list index out of range. I want to know the error caused by env or code?
My enviroment: ubuntu16.04 w…
-
Currently when running `complete:overrides:apply` and `complete:peer-vpc:apply` an error is often reported due to a lack of dependency between the vpg being attached and the route table creation since…
-
Hi I have noticed that at the beginning of the training while using VPG and DDPG in continuous spaces, the action array generated without action exploration is always almost zero. Is it normal?
I am …
-
I have tried running the ppo, ddpg, and vpg for the CarRacing-v0 and continuously receive the same ValueError :
ValueError: Can not squeeze dim[1], expected a dimension of 1, got 96 for 'v/Squeeze'…