Through learning this course, let me some of the reinforcement learning algorithm have must understand, at the same time realize the formula is the foundation of understanding is the key, knock code adjustment and need patience!
Live for a period of 7, baidu's senior r&d engineer coco teacher mainly introduced the Q - Learning, Sarsa and DQN, Policy Gradient, and DDPG these algorithms, the teacher tells his ability and programming practice to explain the knowledge ability to let the people praise!
Through this course of study, also let I realized one kind of beautiful coco and careful patient shaw teacher, to thank the teachers hard for us to pay these days! Thank you!