A2C Agent playing PandaReachDense-v3
This is a trained model of a A2C agent playing PandaReachDense-v3 using the stable-baselines3 library.
Usage (with Stable-baselines3)
import os
import gymnasium as gym
import panda_gym
from huggingface_sb3 import load_from_hub, package_to_hub
from stable_baselines3 import A2C
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
from stable_baselines3.common.env_util import make_vec_env
from huggingface_hub import notebook_login
env_id = "PandaReachDense-v3"
# Create the env
env = gym.make(env_id)
# Get the state space and action space
s_size = env.observation_space.shape
a_size = env.action_space
env = make_vec_env(env_id, n_envs=4)
# Adding this wrapper to normalize the observation and the reward
env = VecNormalize(env, norm_obs=True, norm_reward=True, clip_obs=10.)
model = A2C(
policy = "MultiInputPolicy",
env = env,
verbose=1,
)
# Train
model.learn(1_000_000)
# Save the model and VecNormalize statistics when saving the agent
model.save("a2c-PandaReachDense-v3")
env.save("vec_normalize.pkl")
from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
# Load the saved statistics
eval_env = DummyVecEnv([lambda: gym.make("PandaReachDense-v3")])
eval_env = VecNormalize.load("vec_normalize.pkl", eval_env)
# We need to override the render_mode
eval_env.render_mode = "rgb_array"
# do not update them at test time
eval_env.training = False
# reward normalization is not needed at test time
eval_env.norm_reward = False
# Load the agent
model = A2C.load("a2c-PandaReachDense-v3")
mean_reward, std_reward = evaluate_policy(model, eval_env)
print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
from huggingface_sb3 import package_to_hub
package_to_hub(
model=model,
model_name=f"a2c-{env_id}",
model_architecture="A2C",
env_id=env_id,
eval_env=eval_env,
repo_id=f"sighmon/a2c-{env_id}",
commit_message="With working video",
)
- Downloads last month
- 7
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-0.26 +/- 0.14