RL-算法演进史03：Policy Gradient 与 Actor-Critic 算法演进路线【REINFORCE→Baseline→Actor−Critic→A2C→A3C→TRPO→PPO】

第三章 Policy Gradient 与 Actor-Critic 算法演进路线重点分析：REINFORCE→Baseline→Actor−Critic→A2C→A3C→TRPO→PPO REINFORCE \rightarrow Baseline \rightarrow Actor-Critic \rightarrow A2C \rightarrow A3C \rightarrow TRPO \rightarrow PPOREIN