deep reinforcement learning深度学习.pptxVIP

Human level control through deep reinforcement learning Naiyan Wang P art 1 Q Learning S Q Learning tate A ction R eward Q Learning New State Old State Reward Learning Rate Discount Factor P art 2 Deep Q Learning Traditional Cooking Traditional Cooking Traditional Cooking Traditional Cooking Traditional Cooking End to End Cooking End to End Learning Formulation Target Variable 1 2 3 Results Analysis DQN is good at … DQN is bad at … P art 3 Discussion Q: What is the key contributing factor? Q: How to account for long term dependency ? Discussion A: Almost unlimited training data A: Long short term memory may be the solution Thank You