Stable Baselines3
A high-quality PyTorch implementation library of mainstream reinforcement learning algorithms, including PPO. It provides standardized training interfaces and TensorBoard logging support, and is widely used in robotic simulation and continuous control tasks.
Core Facts
Timeline (last 90 days)
The researcher uses two open-source tools, Stable Baselines3 and PyBullet, for drone reinforcement learning
The Cubic Doggo project uses the PPO algorithm from Stable Baselines3, together with the Gymnasium environment interface and the MuJoCo physics engine, to train a homemade robot dog to stand.
Stable Baselines3 is based on PyTorch and provides high-quality implementations of algorithms such as PPO, SAC, and TD3
All Facts (3)
Stable Baselines3 is based on PyTorch and provides high-quality implementations of algorithms such as PPO, SAC, and TD3
65%UnverifiedThe researcher uses two open-source tools, Stable Baselines3 and PyBullet, for drone reinforcement learning
50%UnverifiedThe Cubic Doggo project uses the PPO algorithm from Stable Baselines3, together with the Gymnasium environment interface and the MuJoCo physics engine, to train a homemade robot dog to stand.
50%