Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees.
Siliang ZengTianyi ChenAlfredo GarciaMingyi HongPublished in: CoRR (2021)
Keyphrases
- learning algorithm
- actor critic
- dynamic programming
- reinforcement learning
- convergence proof
- multi agent systems
- search space
- neuro fuzzy
- neural network
- objective function
- gradient method
- cost function
- computational complexity
- multi agent
- least squares
- simulated annealing
- linear programming
- optimal policy
- monte carlo
- optimization method
- np hard
- model free
- single agent
- policy iteration
- recursive least squares
- policy gradient
- cooperative