Approximate dynamic programming solutions of multi-agent graphical games using actor-critic network structures.
Mohammed I. AbouheafFrank L. LewisPublished in: IJCNN (2013)
Keyphrases
- approximate dynamic programming
- actor critic
- reinforcement learning
- multi agent
- linear program
- dynamic programming
- step size
- policy iteration
- multi agent systems
- control policy
- average cost
- markov decision processes
- optimal solution
- model free
- game theory
- stochastic games
- reinforcement learning algorithms
- temporal difference
- function approximation
- machine learning
- linear programming
- least squares
- multiple agents
- finite state
- state space
- multi objective
- evolutionary algorithm
- learning algorithm