Model-Free Finite-Horizon Zero-Sum Differential Games for Nonlinear Systems.
Dezheng WangYuqi ZhangChenyang XuBin ZhangPublished in: IC-NIDC (2023)
Keyphrases
- nonlinear systems
- finite horizon
- model free
- stochastic games
- markov decision processes
- reinforcement learning
- reinforcement learning algorithms
- optimal policy
- adaptive control
- average reward
- infinite horizon
- game theory
- policy iteration
- nash equilibria
- markov decision process
- function approximation
- fuzzy control
- control law
- state space
- learning rate
- rl algorithms
- fuzzy systems
- finite state
- fuzzy controller
- nash equilibrium
- temporal difference
- optimal control
- fuzzy model
- long run
- multistage
- average cost
- partially observable markov decision processes
- sufficient conditions
- dynamic programming
- control system
- real time
- single agent
- decision problems
- fuzzy logic
- mobile robot
- learning algorithm