Kaggle launched a competition that challenged participants to train an AI agent to play football in the Google Research Football Environment. As a big football fan since childhood, I thought this would be a great opportunity for me to apply reinforcement learning (my favorite ML subject!) to a very interesting scenario that I am personally connected to.

     
Application of Style Transfer as an data augmentation technique to improve model’s robustness.

Donkey Car trained with Double Deep Q Learning (DDQN) in Unity Simulator.

OpenAI hosted a contest challenging participants to create the best agent for playing custom levels of the classic game Sonic the Hedgehog, without having access to those levels during development. The goal of this competition is to come up with a meta-learning algorithm that can transfer learning from a set of training levels to a set of previous unseen test levels. This is very interesting as most RL algorithms are tested in the same environment where they are trained, hence completely ignoring the important question whether the agent can be generalized to previously unseen environments.

    
Instruct DFP agent to change objective (at test time) from pick up Health Packs (Left) to pick up Poision Jars (Right). The ability to pursue complex goals at test time is one of the major benefits of DFP.