README.md

metadata

library_name: stable-baselines3
tags:
  - PandaReachDense-v3
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: PandaReachDense-v3
          type: PandaReachDense-v3
        metrics:
          - type: mean_reward
            value: '-0.22 +/- 0.12'
            name: mean_reward
            verified: false

PPO Agent playing PandaReachDense-v3

This is a trained model of a PPO agent playing PandaReachDense-v3 using the stable-baselines3 library.

Usage (with Stable-baselines3)

TODO: Add your code

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub, package_to_hub
from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize

env_id = "PandaReachDense-v3"
env = gym.make(env_id)
env = make_vec_env(env_id, n_envs=4)
env = VecNormalize(env, training=True, norm_obs=True, norm_reward=True, gamma=0.5, epsilon=1e-10, norm_obs_keys=None)

model =  PPO("MultiInputPolicy", env, verbose=1)
model.learn(1_000_000)

eval_env = DummyVecEnv([lambda: gym.make("PandaReachDense-v3")])
eval_env = VecNormalize.load("vec_normalize.pkl", eval_env)
eval_env.render_mode = "rgb_array"
eval_env.training = False
# reward normalization is not needed at test time
eval_env.norm_reward = False


model = PPO.load("Slay-PandaReachDense-v3")
mean_reward, std_reward = evaluate_policy(model, eval_env)
print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
...