This projects will implement a framework for double deep Q-Learning and some asynchronous methods for DeepRL including asynchronous one-step Q-learning, asynchronous one-step Sarsa, asynchronous n-step Q-learning and asynchronous advantage actor-critic. It will also refactor the existing neural network components to make it more compatible with DeepRL.

Organization

Student

Shangtong Zhang

Mentors

  • Marcus Edel
close

2017