Google I/O 2019 | TF-Agents: A Flexible Reinforcement Learning Library for TensorFlow

TF-Agents is a clean, modular, and well-tested open-source library for Deep Reinforcement Learning with TensorFlow. This session will cover recent advancements in Deep RL, and show how TF-Agents can help to jump start your project. You will also see how TF-Agent library components can be mixed, matched, and extended to implement new RL algorithms.


Speakers: Sergio Guadarrama and Eugene Brevdo

Session ID: TFA7A8

Previous Google I/O 2019 | Machine Learning Fairness: Lessons Learned
Next Statistics for Dummies: The Normal Distribution