Multi-agent Actor-Critic Reinforcement Learning Based In-network Load Balance.
Tianle MaiHaipeng YaoZehui XiongSong GuoDusit Tao NiyatoPublished in: GLOBECOM (2020)
Keyphrases
- reinforcement learning
- load balance
- actor critic
- multi agent
- load balancing
- temporal difference
- computing resources
- function approximation
- reinforcement learning algorithms
- policy gradient
- round robin
- approximate dynamic programming
- scheduling algorithm
- neuro fuzzy
- policy iteration
- state space
- multi agent systems
- markov decision processes
- gradient method
- optimal policy
- model free
- learning algorithm
- partially observable markov decision processes
- optimal control
- temporal difference learning
- peer to peer
- rl algorithms
- supervised learning
- limited resources
- function approximators
- learning problems
- quality of service
- state action
- reinforcement learning methods
- dynamic programming
- wireless sensor networks