Hands-on Reinforcement Learning with Ray and RLlib
May 27, 2020
San Francisco, CA
Reinforcement learning requires a variety of computational patterns: data processing, simulations, model training, model serving. etc. Few frameworks efficiently support all these patterns at scale. In this hands-on tutorial, we’ll see how Ray and RLlib seamlessly and efficiently support these workloads, providing an ideal platform for building RL applications. We’ll deep dive into Ray and RLlib APIs. We’ll train and serve an RL-based application.