RLlib
Scalable, state of the art reinforcement learning
RLlib is the industry-standard reinforcement learning Python framework built on Ray. Designed for quick iteration and a fast path to production, it includes 25+ latest algorithms that are all implemented to run at scale and in multi-agent mode.
Why RLlib?
Learn what makes RLlib stand out and why it’s the reinforcement learning library of choice for companies like Wildlife Studios, McKinsey / QuantumBlack and others.
Vibrant community
Reinforcement learning is hard. Easily find code examples and connect with other developers and experts.
Distributed-first
Iterate quickly without needing to rewrite again to go to production or scale to a large cluster.
State of the art
Choose from the latest and greatest in reinforcement learning algorithms to find the one best suited for your problem. Enjoy multi-agent support in all.
Supports external simulators
Optimize your policies using an industry- or problem-specific external simulator. Connect simulations to RLlib via its PolicyServer/Client architecture.
Seriously fast
Experience really fast policy evaluation, with lower overhead than most algorithms.
Tap into Ray ecosystem
Find the perfect set of hyperparameters using Ray Tune. Serve your trained model in a massively parallel way with Ray Serve.
Do more with Ray
Expand your Ray journey beyond reinforcement learning and bring fast and easy distributed execution to other use cases.
Try it yourself
Install RLlib (and PyTorch for this example) with pip install 'ray[rllib]' torch and give this example a try.
from ray import tune
from ray.rllib.agents.ppo import PPOTrainer
tune.run(PPOTrainer, config={
"env": "CartPole-v0",
"framework": "torch",
"log_level": "INFO"
})
See RLlib in action
Learn how your peers are using RLlib to scale up and accelerate their reinforcement learning workloads.
Wildlife Studios
Mobile gaming giant, Wildlife Studios improved player lifetime value by creating and serving better in-game offers with RLlib.
Pathmind
Pathmind shares how they use RLlib for reinforcement learning in industrial applications, and why they think this approach can outperform others.
Two Sigma
Learn how Financial Services company, Two Sigma, got a 24x speedup on their reinforcement learning use case with RLlib.
O'Reilly Learning Ray Book
Get your free copy of early release chapters of Learning Ray, the first and only comprehensive book on Ray and its ecosystem, authored by members on the Ray engineering team
