A Federated Learning and Deep Reinforcement Learning-Based Method with Two Types of Agents for Computation Offload.
Song LiuShiyuan YangHanze ZhangWeiguo WuPublished in: Sensors (2023)
Keyphrases
- reinforcement learning
- prior knowledge
- dynamic programming
- pairwise
- learning process
- learning algorithm
- policy search
- cooperative
- significant improvement
- probabilistic model
- reinforcement learning methods
- learning agent
- model free
- detection method
- multi agent
- similarity measure
- data sources
- semi supervised
- supervised learning
- distributed systems
- unsupervised learning
- multi agent systems
- mobile agents
- learning tasks
- learning problems
- learning mechanism
- objective function
- learning agents
- training data