Hessian Aided Policy Gradient.
Zebang ShenAlejandro RibeiroHamed HassaniHui QianChao MiPublished in: ICML (2019)
Keyphrases
- policy gradient
- gradient method
- reinforcement learning
- actor critic
- parametric optimization
- function approximation
- step size
- optimal control
- model free reinforcement learning
- reinforcement learning algorithms
- variance reduction
- approximation methods
- partially observable markov decision processes
- average reward
- single agent
- machine learning
- state action
- dynamic bayesian networks
- radial basis function
- monte carlo
- multi agent
- learning algorithm