Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems.
Bo PangZhong-Ping JiangPublished in: CoRR (2021)
Keyphrases
- stochastic systems
- optimal control
- reinforcement learning
- control problems
- adaptive control
- dynamic programming
- control system
- non stationary
- control strategy
- sample path
- stochastic models
- control method
- action selection
- state space
- confidence intervals
- control algorithm
- model free
- temporal difference
- markov decision process
- function approximation
- markov decision processes
- learning algorithm