Closed NUSLCC closed 10 months ago
The documentation was not up to date. It should be fixed now. Use the following code:
import gymnasium as gym
import panda_gym
from stable_baselines3 import DDPG
env = gym.make("PandaReach-v3")
model = DDPG(policy="MultiInputPolicy", env=env)
model.learn(30_000)
Thanks! It works in my environment now.
Tried and failed with panda-gym==2.0.0 as required, gym==0.26.2, stable-baseline3==2.1.0 Can anyone provide a clue of how to run the demo train code, thanks!! Also tried to downgrade the gym==0.21.0 by #19, still failed.![image](https://github.com/qgallouedec/panda-gym/assets/125369836/9b92975d-f0ee-44f3-847c-bb9c8ec3f4c3)