Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms.
Yanwei JiaXun Yu ZhouPublished in: CoRR (2021)
Keyphrases
- actor critic
- policy gradient
- policy gradient methods
- optimal control
- reinforcement learning
- learning algorithm
- natural actor critic
- policy iteration
- temporal difference
- neuro fuzzy
- approximate dynamic programming
- function approximation
- reinforcement learning algorithms
- reinforcement learning methods
- partially observable markov decision processes
- rl algorithms
- dynamical systems
- gradient method
- model free
- learning problems
- learning tasks
- state space
- markov decision processes
- search space
- machine learning
- optimal policy
- approximation methods
- variance reduction
- linear program
- monte carlo