Implementation of two early-stage DRL models.
DQN [1] to teach PC the Pong game.
Early-stage attention model [2].
[1] Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." Nature 518.7540 (2015): 529.
[2] Mnih, Volodymyr, Nicolas Heess, and Alex Graves. "Recurrent models of visual attention." Advances in neural information processing systems. 2014.