tailieunhanh - Lecture Machine learning (2014-2015) - Lecture 12: Reinforcement learning

This lecture introduces you reinforcement learning. In this chapter, students will be able to understand: Learning to act through trial and error, deep reinforcement learning, attention-based game agent, delayed rewards,. Inviting you refer. | The Promise of Reinforcement Learning Learning to act through trial and error. lEnvữonment observation reward action An agent interacts with an environment and learns by maximizing a scalar reward signal. No models labels demonstrations or any other human-provided supervision signal. Representation has been a challenge missing. Agent Volodymyr Mnih Deep Reinforcement Learning Combining deep neural networks with RL. Learn to act from high-dimensional sensory inputs. Is a noisy sparse and delayed reward signal sufficient for training deep networks Credit assignment problem. observations reward action Volodymyr Mnih

TỪ KHÓA LIÊN QUAN