Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian.
Paria RashidinejadHanlin ZhuKunhe YangStuart RussellJiantao JiaoPublished in: CoRR (2022)
Keyphrases
- function approximation
- reinforcement learning
- augmented lagrangian
- temporal difference
- model free
- radial basis function
- dynamic programming
- learning tasks
- td learning
- reinforcement learning algorithms
- optimal solution
- total variation
- constrained optimization
- temporal difference methods
- convex optimization
- function approximators
- learning algorithm
- neural network
- optimal control
- supervised learning
- constrained optimization problems
- machine learning