/Deep-QNetwork_gaming

Borrowing gaming DQN agents for eventual appliction in Financial data

Primary LanguagePython

Deep Reinforcement Learning from Games to Value Investing

What is it?

State-of-the art deep reinforcement learning algorithm in Tensorflow and Python for eventual application to non-gaming environments.

The performance above came after:

  • Playing 1.75 million games over
  • ~ 2 days of training
  • 3 x 2D ConvNet, and
  • a Linear Annealed Greedy EPS Policy

Todos

  • Convert agent to work on MktCap / GVA application