deep_q_learning Very simple code using pytorch to realize reinforcement learning. Support Q learning Q learning Value based method Deep Q Network (DQN) Double DQN Dueling DQN Policy gradient navie Policy gradient navie Actor critic Deep Deterministic Policy Gradient (DDPG) Result Policy_gradient_naive (CartPole-v1 and MountainCar-v0) DQN family DDPG (Pendulum-v0)
