Model-free algorithm for consensus of discrete-time multi-agent systems using reinforcement learning method.
Mingkang LongQing AnHousheng SuHui LuoJin ZhaoPublished in: J. Frankl. Inst. (2023)
Keyphrases
- model free
- reinforcement learning
- dynamic programming
- reinforcement learning algorithms
- function approximation
- policy evaluation
- policy iteration
- learning algorithm
- segmentation algorithm
- k means
- objective function
- function approximators
- state space
- multi agent
- linear programming
- support vector machine svm
- machine learning
- learning experience
- temporal difference
- rl algorithms
- training data
- fitted q iteration