stable-baselines3

What problem does it solve?

This Skill provides a robust framework for developing and training Reinforcement Learning agents, simplifying complex RL workflows from environment setup to model evaluation.

Core Features & Use Cases

• Algorithm Implementation: Access to state-of-the-art RL algorithms like PPO, SAC, DQN.
• Custom Environment Support: Easily integrate your own custom environments.
• Training & Evaluation: Tools for efficient training, monitoring, and performance assessment.
• Use Case: Train an agent to play a game, control a robot arm, or optimize a complex system by defining its environment and letting SB3 handle the learning process.

Quick Start

Use the stable-baselines3 skill to train a PPO agent on the CartPole-v1 environment for 100,000 timesteps.