TensorFlow implementation of Deep Q-Learning Network (DQN) (Mnih et al., 2013) on classical reinforcement learning problems (cart pole balancing and mountain car). This implementation involves experience replay, fixing target network, double Q-learning.
Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." arXiv preprint arXiv:1312.5602 (2013).
Van Hasselt, Hado, Arthur Guez, and David Silver. "Deep reinforcement learning with double Q-learning." CoRR, abs/1509.06461 (2015).