该项目旨在促进强化学习的理论基础，并促进强化学习和计算机科学领域的研究人员之间的新合作。
官方网址
- 2020(8.19-12.18): Theory of Reinforcement Learning
- 2020(8.31-9.4): Theory of Reinforcement Learning Boot Camp
- 2020(9.28-10.2): Deep Reinforcement Learning
- 2020(10.26-10.30): Mathematics of Online Decision Making
- 2020(11.30-12.4): Reinforcement Learning from Batch Data and Simulation
视频网址
- Theory of Reinforcement Learning Boot Camp: [youtube]
演讲内容
[1] Theory of Reinforcement Learning Boot Camp
- Planning and Markov Decision Processes (Part 1)
- Planning and Markov Decision Processes (Part 2)
- Online Learning and Bandits (Part 1)
- Online Learning and Bandits (Part 2)
- Optimizing Intended Reward Functions: Extracting All the Right Information From All the Right Places
- Online Learning in MDPs (Part 1)
- Online Learning in MDPs (Part 2)
- Batch (Offline) RL (Part 1)
- Batch (Offline) RL (Part 2)
- The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
- Statistical Considerations in Reinforcement Learning (Part 1): Statistical Inference and Non-Regularity
- Statistical Considerations in Reinforcement Learning (Part 1): Statistical Inference and Non-Regularity
- Statistical Considerations in Reinforcement Learning (Part 2): Emerging Application Areas and Challenges
- Statistical Considerations in Reinforcement Learning (Part 2): Emerging Application Areas and Challenges
- Learning to Act from Observations
- Control Fundamentals
- Every Optimization Problem Is a Quadratic Program: Applications to Dynamic Programming and Q-Learning
- Basics of Algorithm Design and Analysis
- Recent Results on RL With Gradient Free Optimization
- Gradient-Free Optimization With Applications to Power Systems
- Stochastic Programming Approach to Optimization Under Uncertainty (Part 1)
- Stochastic Programming Approach to Optimization Under Uncertainty (Part 2)
- Simulation Methodology: An Overview (Part 1)
- Simulation Methodology: An Overview (Part 2)
- A Few Challenge Problems from Robotics