Completed
Vignette: UCB and Monte Carlo Tree Search
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Reinforcement Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Birds-eye view of RL
- 3 Illustrative application: RL in personal health
- 4 General thrust
- 5 Direction: Exploiting structure in RL
- 6 Vignette: Q-learning with low rank structure
- 7 Vignette: Model-free versus model-based method
- 8 Estimate dynamics or value functions for LQR? - Linear state space model with quadratic reward function
- 9 Performance of LSTD versus model-based metho
- 10 Direction: Exploration/exploitation beyond bandi
- 11 Vignette: Q-learning with UCB
- 12 Vignette: UCB and Monte Carlo Tree Search
- 13 Direction: From worst-case to instance-optimalit
- 14 Vignette: Instance-optimality of TD learning?
- 15 Instance-optimality in policy evaluation
- 16 Direction: RL in offline settings and causal inferen
- 17 Some future directions exploiting methods from cal inferences instrumental variables propensity score, doubly robust methods, synthetic controls
