coreylynch/async-rl

Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"

94 best points · 2 comments · 2 Hacker News posts · 1,004 GitHub stars · View on GitHub

Hacker News discussions

• Deep Reinforcement Learning Using Keras and OpenAI Gym (94 points, 2 comments, by fchollet, 2016-06-10)
• Asyncronous RL in Tensorflow and Keras and OpenAI's Gym (1 points, 0 comments, by mau, 2016-06-08)