RL Baselines Zoo is a comprehensive training framework and collection of pre-trained RL agents using Stable-Baselines3. It offers tools for training, tuning, and evaluating RL algorithms across many standard environments, including MuJoCo, Atari, and robotics simulations. Designed for reproducible RL research and benchmarking, it includes scripts, hyperparameter presets, and best practices for training robust agents.

Features

  • Collection of optimized hyperparameters for many environments
  • Supports Stable-Baselines3 RL algorithms (PPO, A2C, DDPG, SAC, TD3)
  • Tools for automated training, evaluation, and saving of agents
  • Includes benchmarking and comparison framework
  • Provides pre-trained models for direct evaluation and transfer learning
  • Compatible with custom environments and Gym-based setups

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow RL Baselines Zoo

RL Baselines Zoo Web Site

Other Useful Business Software
Forever Free Full-Stack Observability | Grafana Cloud Icon
Forever Free Full-Stack Observability | Grafana Cloud

Our generous forever free tier includes the full platform, including the AI Assistant, for 3 users with 10k metrics, 50GB logs, and 50GB traces.

Built on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
Create free account
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of RL Baselines Zoo!

Additional Project Details

Programming Language

Python

Related Categories

Python Reinforcement Learning Algorithms

Registered

2025-03-13