Completely model-free RL-based consensus of continuous-time multi-agent systems.
Xiaoling WangHousheng SuPublished in: Appl. Math. Comput. (2020)
Keyphrases
- model free
- multi agent systems
- reinforcement learning
- reinforcement learning algorithms
- rl algorithms
- function approximation
- multi agent
- state space
- temporal difference
- markov chain
- policy iteration
- game theory
- cooperative
- learning process
- policy evaluation
- hierarchical reinforcement learning
- data mining
- stochastic games