RLlib: Scalable Reinforcement Learning
RLlib is an open-source library for reinforcement learning that offers both a collection of reference algorithms and scalable primitives for composing new ones.
Learn more about RLlib's design by reading the ICML paper.
pip install tensorflow # or tensorflow-gpu pip install ray[rllib]
You might also want to clone the Ray repo for convenient access to RLlib helper scripts:
git clone https://github.com/ray-project/ray cd ray/python/ray/rllib
- RLlib Environments Overview
- OpenAI Gym
- Interfacing with External Agents
- Batch Asynchronous
- High-throughput architectures
Models and Preprocessors
- RLlib Models and Preprocessors Overview
- Built-in Models and Preprocessors
- Custom Models
- Custom Preprocessors
- Customizing Policy Graphs
- Model-Based Rollouts
If you encounter errors like
blas_thread_init: pthread_create: Resource temporarily unavailable when using many workers,
OMP_NUM_THREADS=1. Similarly, check configured system limits with
ulimit -a for other resource limit errors.
For debugging unexpected hangs or performance problems, you can run
ray stack to dump
the stack traces of all Ray workers on the current node. This requires py-spy to be installed.