README.md

---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: AntBulletEnv-v0
      type: AntBulletEnv-v0
    metrics:
    - type: mean_reward
      value: 1834.41 +/- 107.15
      name: mean_reward
      verified: false
---

# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).

## Usage (with Stable-baselines3)
TODO: Add your code


```python
import pybullet_envs
import panda_gym
import gym

import os

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

#Environment 1: AntBulletEnv-v0
env_id = "AntBulletEnv-v0"
# Create the env
env = gym.make(env_id)

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)

#create A2C model
model = A2C(policy = "MlpPolicy",
            env = env,
            gae_lambda = 0.9,
            gamma = 0.99,
            learning_rate = 0.00096,
            max_grad_norm = 0.5,
            n_steps = 8,
            vf_coef = 0.4,
            ent_coef = 0.0,
            seed=11,
            policy_kwargs=dict(
            log_std_init=-2, ortho_init=False),
            normalize_advantage=False,
            use_rms_prop= True,
            use_sde= True,
            verbose=1)

#train agent
model.learn(1_500_000)

# Save the model and VecNormalize statistics when saving the agent
model.save("a2c-AntBulletEnv-v0")
env.save("vec_normalize.pkl")
```