Continual Reinforcement Learning Formulation for Zero-Sum Game-Based Constrained Optimal Tracking.
Behzad FarzaneganSarangapani JagannathanPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2023)
Keyphrases
- reinforcement learning
- dynamic programming
- learning process
- optimal control
- optimal solution
- closed form
- kalman filter
- lagrange multipliers
- real time
- function approximation
- particle filter
- object tracking
- learning systems
- visual tracking
- learning tools
- optimal policy
- game theory
- model free
- markov decision process
- machine learning