-
现在的数据流程是
1. policy_old = policy
2. 使用policy_old去交互,生成数据
3. 使用数据去更新policy模型
4. policy_old = policy
在这个流程中,policy_old完全没有作用,或者说代码中去掉policy_old,使用policy进行替代,最终的结果完全一致
所以这个真的是PPO么??
-
https://ja1r0.github.io/2018/01/09/TRPO%E8%AE%BA%E6%96%87%E9%98%85%E8%AF%BB/
Ja1r0 updated
6 years ago
-
I've tried to use TRPO to create a model for `CartPole-v0` by following the instructions on your [OpenAI Gym page](https://gym.openai.com/evaluations/eval_4QXCRAATTDqakJV0YZlJ4g#reproducibility), chan…
-
Hi, I am a newcomer to drl. When I try to read trpo_step in trpo.py, I notice that you use a linesearch method instead of trust region for numerical optimization. So I want to know why you choose that…
-
I'm trying to convert the coordinates of markers from the visual coordinates to canvas coordinates. If I do this with a camera with fov=0, everything works fine:
``` python
import numpy as np
from vi…
-
It will be great to add performance evaluation and comparisons of algorithms available in ChainerRL.
-
The link of the slides is invalid – [slides #1 (trpo)](https://docs.google.com/presentation/d/15Z_AVBsO9VuOSZ5uY-Q4by3tHKiRSENchhAKHhCxIOc/present?token=AC4w5VgM6o7lCOmwtNFI3lfzyPv2PHOpRQ%3A1511795215…
-
После того, как сделаешь проект, сука запили в нем классы для всех моделей из проекта TRPO.Models, чтобы они назывались имяDB типа FlightDB. В них сделать методы для получения всех записей, получения …
-
This is more of a question than an issue. I noticed that in the implementation of the above-mentioned algorithms, action limits are not taken into account. Environments handle this clipping internally…
-
All of the scripts trpo_gym_tf_cartpole.py, trpo_gym_tf_cartpole.py, trpo_cartpole_pickled.py, ddpg_cartpole.py stopped working just after the start with the same error message:
```
rllab\examples>…