RL2_policy_gradients_mainly

https://flyyufelix.github.io/2017/10/12/dqn-vs-pg.html   ***Deep Q Network vs Policy Gradients - An Experiment on VizDoom with Keras

http://karpathy.github.io/2016/05/31/rl/     ***Deep Reinforcement Learning: Pong from Pixels

https://www.jianshu.com/p/a3432c0e1ef2   ***DDPG and TORCS(The Open Racing Car Simulator)

https://lilianweng.github.io/lil-log/2018/04/08/policy-gradient-algorithms.html#a2c   ***Policy Gradient Algorithms

https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-8-asynchronous-actor-critic-agents-a3c-c88f72a5e9f2   ***Simple Reinforcement Learning with Tensorflow Part 8: Asynchronous Actor-Critic Agents (A3C)

https://towardsdatascience.com/proximal-policy-optimization-ppo-with-sonic-the-hedgehog-2-and-3-c9c21dbed5e   ***Proximal Policy Optimization (PPO) with Sonic the Hedgehog 2 and 3

https://blog.csdn.net/Pony017/article/details/81146374   ***从REINFORCE到PPO，看Policy Gradient的前世今生