README.md

---
library_name: stable-baselines3
tags:
- PandaPickAndPlace-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: PandaPickAndPlace-v3
      type: PandaPickAndPlace-v3
    metrics:
    - type: mean_reward
      value: -50.00 +/- 0.00
      name: mean_reward
      verified: false
---

# **A2C** Agent playing **PandaPickAndPlace-v3**
This is a trained model of a **A2C** agent playing **PandaPickAndPlace-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).

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


```python

%%capture
!apt install python-opengl
!apt install ffmpeg
!apt install xvfb
!pip3 install pyvirtualdisplay


from pyvirtualdisplay import Display

virtual_display = Display(visible=0, size=(1400, 900))
virtual_display.start()

!pip install stable-baselines3[extra]
!pip install gymnasium
!pip install huggingface_sb3
!pip install huggingface_hub
!pip install panda_gym

import os

import gymnasium as gym
import panda_gym
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

env_id = "PandaPickAndPlace-v3"

env = gym.make(env_id)
env = make_vec_env(env_id, n_envs=4)
env = VecNormalize(env, clip_obs = 10)
model = A2C("MultiInputPolicy", env, verbose=1)
model.learn(1_000_000)

model.save("a2c-PandaPickAndPlace-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("PandaPickAndPlace-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-PandaPickAndPlace-v3")

mean_reward, std_reward = evaluate_policy(model, eval_env)

print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
...
```