AI Plays Football For Science!

El Clasico
Google Research Football Environment Gameplay
Pratham’s quest for the diamond
A beautiful way to drive and finish a counter-attack
The average goal difference of agent versus opponent at different difficulty levels for different baselines (Number of steps). The Easy opponent can be beaten by a DQN agent trained for 20 million steps, while the Medium and Hard opponents require a distributed algorithm such as IMPALA that is trained for 500 million steps.
GO REAL BAYESIANS! You can do it! Probably.

Further Reading:

  1. Google Research Football: A Novel Reinforcement Learning Environment
  2. Github: Google Research Football
  3. Instructions to Set it up on Your Computer
  4. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
  5. Human Level Control Through Deep Reinforcement Learning

More from Journal

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store