On the Global Convergence of Momentum-based Policy Gradient.
Yuhao DingJunzi ZhangJavad LavaeiPublished in: CoRR (2021)
Keyphrases
- global convergence
- policy gradient
- convergence rate
- learning rate
- gradient method
- convergence speed
- optimization methods
- global optimum
- reinforcement learning
- step size
- function approximation
- approximation methods
- particle swarm optimization algorithm
- reinforcement learning algorithms
- neural network
- optimal control
- variance reduction
- optimization problems
- optimization method
- partially observable markov decision processes
- least squares
- reinforcement learning methods