Completed
Definition
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Decision Awareness in Reinforcement Learning - End-to-End Optimization Approaches
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Definition
- 3 End-to-End Principle
- 4 What is neural network?
- 5 Automatic Differentiation
- 6 Computational Graph
- 7 Reverse and Forward Mode
- 8 Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation
- 9 Optimal Model Design Problem (OMD)
- 10 Smooth Bellman Optimality Equations
- 11 Connection between OMD and Rust (1988)
- 12 Bilevel Optimization (Bard 1998)
- 13 Implicit and Iterative Differentiation
- 14 Benefits under Model Misspecification
- 15 Function Approximation and Distractor States
- 16 Performance under Model Misspecification
- 17 Continuous-Time Meta-Learning with Forward Mode Dif- ferentiation.
- 18 Gradient Flow-based Meta-Learning
- 19 Time irreversibility
- 20 Memory-efficient meta-gradients
- 21 Consequence
- 22 Empirical Efficiency of COML
- 23 Nonlinear Trajectory Optimization
- 24 Extragradient Method
- 25 Trajectory Optimization with Learned Model
