Junfeel/pusher-v5-pro

PPO Agent for Gymnasium MuJoCo Pusher-v5

This model is a high-performance PPO agent controlling a 7-DOF robotic arm to push a cylinder towards a target in Gymnasium MuJoCo Pusher-v5.

Trained and exported directly via MuJoCo Pusher RL Studio Pro.

🦾 Environment Details

• Environment: Pusher-v5 (Gymnasium / MuJoCo)
• Algorithm: PPO (Stable-Baselines3)
• Observation Space: 23 dimensions (joint angles, velocities, tip, object, goal coordinates)
• Action Space: 7 dimensions (torque controls in range [-2.0, +2.0] Nm)

🚀 Usage (Stable-Baselines3)

import gymnasium as gym
from stable_baselines3 import PPO

env = gym.make("Pusher-v5", render_mode="human")
model = PPO.load("ppo_pusher_latest.zip")

obs, _ = env.reset()
for _ in range(1000):
    action, _ = model.predict(obs, deterministic=True)
    obs, reward, done, truncated, _ = env.step(action)
    if done or truncated:
        obs, _ = env.reset()
env.close()