1.4.3 Reinforcement Learning

 Virtual Games. Compared with the real environment, virtual game platforms can both train and test reinforcement learning algorithms and can avoid interference from irrelevant factors while also minimizing the cost of experiments. Currently, commonly used virtual game platforms include OpenAI Gym, OpenAI Universe, OpenAI Roboschool, DeepMind OpenSpiel, and MuJoCo, and commonly used reinforcement learning algorithms include DQN, A3C, A2C, and PPO. In the field of Go, the DeepMind AlphaGo program has surpassed human Go experts. In Dota2 and StarCraft games, the intelligent programs developed by OpenAI and DeepMind have also defeated professional teams under restriction rules.

Robotics. In the real environment, the ocntrol of robots has also made some progress. For example, UC Berkeley Lab has made a lot of progress in the areas of imitation learning, meta learning, and few-shot learning in the field of robotics. Boston Dynamics has made gratifying achievements in robot applications. The robots it manufactures perform well on tasks such as complex terrain walking and multi-agent collaboration (Figure 1-19).

Autonomous driving is considered as an application direction of reinforcement learning in the short term. Many companies have invested a lot of resources in autonomous driving, such as Baidu, Uber, and Google. Apollo from Baidu has begun trial operations in Beijing, Xiong'an, Wuhan, and other places. Figure 1-20 shows Baidu's self-driving car Apollo.