Integral Policy Iterations for Reinforcement Learning Problems in Continuous Time and Space.
Jae Young LeeRichard S. SuttonPublished in: CoRR (2017)
Keyphrases
- reinforcement learning problems
- reinforcement learning algorithms
- reinforcement learning methods
- action space
- state space
- reinforcement learning
- markov decision problems
- natural actor critic
- function approximators
- dynamical systems
- neural network
- markov chain
- policy iteration
- optimal solution
- finite state
- action selection
- optimal control
- monte carlo
- machine learning