pufferlib

Topics in the source

• PufferLib - High-Performance Reinforcement Learning
• Overview
• When to Use This Skill
• Core Capabilities
• 1. High-Performance Training (PuffeRL)
• 2. Environment Development (PufferEnv)
• 3. Vectorization and Performance
• 4. Policy Development

PufferLib is a high-performance reinforcement learning library designed for fast parallel environment simulation and training. It achieves training at millions of steps per second through optimized vectorization, native multi-agent support, and efficient PPO implementation (PuffeRL). The library provides the Ocean suite of 20+ environments and seamless integration with Gymnasium, PettingZoo, and specialized RL frameworks. Use this skill when: Training RL agents with PPO on any environment (single or multi-agent) Creating custom environments using the PufferEnv API Optimizing performance for parallel environment simulation (vectorization) Integrating existing environments from Gymnasium, PettingZoo, Atari, Procgen, etc. Developing policies with CNN, LSTM, or custom architectures Scaling RL to millions of steps per second for faster experimentation Multi-agent RL with native multi-agent environment support PuffeRL is PufferLib's optimized PPO+LSTM training algorithm achieving 1M-4M steps/second. Quick start training: Python training loop: For comprehensive training guidance, read references/training.md for: Complete training workflow and CLI options Hyperparameter tuning with Protein

This is an excerpt. Refer to the complete source and its current requirements.