Discounted linear Q-learning control with novel tracking cost and its stability.
Ding WangJin RenMingming HaPublished in: Inf. Sci. (2023)
Keyphrases
- reinforcement learning
- optimal policy
- dynamic programming
- state space
- real time
- average cost
- cooperative
- control system
- particle filter
- learning algorithm
- multi agent
- lyapunov function
- control method
- kalman filter
- control problems
- reinforcement learning algorithms
- adaptive control
- function approximation
- markov decision processes
- particle filtering
- control strategy
- trajectory tracking