Online Reinforcement Learning in Stochastic Continuous-Time Systems.
Mohamad Kazem Shirani FaradonbehMohamad Sadegh Shirani FaradonbehPublished in: COLT (2023)
Keyphrases
- reinforcement learning
- markov processes
- online learning
- complex systems
- real time
- markov chain
- stochastic approximation
- optimal control
- distributed systems
- knowledge based systems
- monte carlo
- direct policy search
- control policies
- stochastic process
- function approximation
- learning systems
- management system
- state space
- expert systems
- multi agent
- machine learning
- neural network