Coming soon! A Tensor flow implementation of the GA3C algortihm for deep reinforcement learning, as first described in: Mohammad Babaeizadeh, Iuri Frosio, Stephen Tyree, Jason Clemons, Jan Kautz, "GA3C: GPU-based A3C for Deep Reinforcement Learning", The 1st International Workshop on Efficient Methods for Deep Neural Networks, EMDNN 2016 (NIPS 2016), Barcelona, Spain, Dec. 2016, and further developed in: Mohammad Babaeizadeh, Iuri Frosio, Stephen Tyree, Jason Clemons, Jan Kautz, "Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU", submitted to ICLR 2017, Dec. 2016.