-
Hi,
I'm trying to run a custom env from a docker image and encounter some problems with it (documentation suggests the use of RL model zoo, but it doesn't support custom envs):
1. `docker pull sta…
-
**Describe the bug**
PPO2 have bad performance on Atari games. For example, it does not converge on pong.
**Code example**
Using https://github.com/araffin/rl-baselines-zoo:
```
python train.…
-
The acrobot won't stabilize at the equilibrium, it just keeps on spinning around. Why is that? The code can be seen under.
> import gym
>
> from gym import spaces
> from AcrobotEnv import Acrob…
-
When trying to run `~/ParlAI/projects/convai2/baselines/seq2seq/interactive.py`, the following error occurs:
```
Traceback (most recent call last):
File "/home/sogun3/ParlAI/parlai/core/build_dat…
-
I trained a TRPO agent with standard hyperparameters on the Hopper-v2 environment in mujoco for 10M timesteps. At the end of the training iterations, i noticed that the EpRewMean is around 2.39e+03. H…
-
After cloning the rl-baselines3-zoo, I was trying to train my own agent.
By :
**python train.py --algo algo_name --env env_id**
After that, I used
**python enjoy.py --algo td3 --env AntBulletEnv-v…
-
Hello,
I am using a custom environment in pybullet that resets after 500 simulation steps.
I can go through 75000 simulation steps with PPO2 in about 30 mins but with DDPG it's approximately 150…
-
Hi all,
I am trying to follow pybullet quickstart guide and run an example. I want to train minitaur and visualize minitaur robot for academic purposes. I am actually newbie in python environment …
-
There should be a way to see your results that tells you what one should expect if you run the training from scratch. At a minimum, there should be information on a number of training steps and eventu…
-
Hi, thanks for the good repo!
I trained the same agent(a human model on Mujoco) with same environment with PPO2, one is only with DummyVecEnv and the other one with DummyVecEnv and VecNormalize
```p…