Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction.
Jie FengKe WeiJinchi ChenPublished in: CoRR (2024)
Keyphrases
- variance reduction
- policy gradient
- global convergence
- convergence rate
- monte carlo
- global optimum
- gradient method
- optimization methods
- convergence speed
- sample size
- step size
- actor critic
- importance sampling
- reinforcement learning
- reinforcement learning algorithms
- differential evolution
- naive bayes classifier
- generative model
- probabilistic model