Skip to content
Snippets Groups Projects
Commit 9d7b1ba9 authored by Ghelfi Manon's avatar Ghelfi Manon
Browse files

Upload New File

parent 190de6a2
No related branches found
No related tags found
No related merge requests found
import wandb
import gym
import panda_gym
from stable_baselines3 import A2C
import numpy as np
wandb.init(project='panda-reach-joints-dense-v2')
env = gym.make('PandaReachJointsDense-v2')
env = gym.make('PandaReachJointsDense-v2', render_mode="human")
model = A2C("MlpPolicy", env, verbose=1)
model.learn(total_timesteps=500000)
rewards = []
obs = env.reset()
while True:
action, _states = model.predict(obs)
obs, reward, done, info = env.step(action)
rewards.append(reward)
if done:
break
wandb.log({'rewards': np.sum(rewards)})
model.save("panda-reach-joints-dense-v2")
from huggingface_sb3 import push_to_hub
push_to_hub(
repo_id="manonghelfi/panda-reach-joints-dense-v2",
filename="./panda-reach-joints-dense-v2.zip",
commit_message="Added panda-reach-joints-dense-v2 model trained with A2C",
)
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment