Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning.
Jineng RenPublished in: Int. J. Comput. Intell. Syst. (2024)
Keyphrases
- multi agent
- reinforcement learning
- actor critic
- learning algorithm
- dynamic programming
- computational complexity
- cost function
- single agent
- np hard
- optimal solution
- policy gradient
- linear programming
- objective function
- model free
- simulated annealing
- particle swarm optimization
- optimal control
- average reward
- neural network
- control system
- search space
- rl algorithms