Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms.
Yanwei JiaXun Yu ZhouPublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- actor critic
- policy gradient
- policy gradient methods
- optimal control
- reinforcement learning
- learning algorithm
- policy iteration
- gradient method
- temporal difference
- approximate dynamic programming
- neuro fuzzy
- natural actor critic
- partially observable markov decision processes
- model free
- markov decision processes
- reinforcement learning algorithms
- dynamical systems
- function approximation
- variance reduction
- reinforcement learning methods
- learning problems
- state space
- step size
- average reward
- rl algorithms
- search space
- convergence rate
- multi agent systems