课程名称
UCL开放课程:强化学习/Reinforcement Learning学习视频,资源教程下载
课程介绍
该课程为强化学习的基础课,在智能机器人控制中有大量的应用,它的“进阶”版DeepReinforcement Learning(AlphaGo的核心技术之一)。有别于“经典”的控制理论,比如Classical Control Theory (根轨迹、频域设计那些), Robust Control, MPC,Adaptive Control等等,它是Model-Free控制理论,相对来说有更大的自由度吧。它的部分控制策略也是有stability保证的, 具体可以去查查paper吧 (我是自控领域出生,对机器学习领域发展出来的控制理论了解不深)。
课程目录
– Lecture 1: Introduction to Reinforcement Learning
– Lecture 2: Markov Decision Processes
– Lecture 3: Planning by Dynamic Programming
– Lecture 4: Model-Free Prediction
– Lecture 5: Model-Free Control
– Lecture 6: Value Function Approximation
– Lecture 7: Policy Gradient Methods
– Lecture 8: Integrating Learning and Planning
– Lecture 9: Exploration and Exploitation
– Lecture 10: Case Study: RL in Classic Games
评论0