Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation.
Jing DongLi ShenYinggan XuBaoxiang WangPublished in: CoRR (2022)
Keyphrases
- function approximation
- primal dual
- actor critic
- reinforcement learning
- temporal difference
- convergence rate
- policy gradient
- gradient method
- approximate dynamic programming
- linear program
- linear programming
- reinforcement learning algorithms
- neuro fuzzy
- model free
- convex optimization
- learning tasks
- optimal control
- temporal difference learning
- function approximators
- radial basis function
- artificial neural networks
- policy iteration
- learning algorithm
- markov decision processes
- objective function
- machine learning