Deep Reinforcement Learning


Date
Location
CAMALAB Conference Room, East Campus Hangzhou Dianzi University

  • Markov Decision Processes
  • Policy Learning and Value Learning
  • Bellman Equation
  • Model-based and Model-free
  • Q-learning, Policy Gradients, Actor-Critic
  • Experience Replay
  • Applications: Atari Game, Recurrent Attention Model(RAM)

Referfence and Recommend Materials

comments powered by Disqus