Stable Online Computation Offloading via Lyapunov-guided Deep Reinforcement Learning.
Suzhi BiLiang HuangHui WangYing-Jun Angela ZhangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- online learning
- equilibrium point
- function approximation
- model free
- control theory
- stability analysis
- reinforcement learning algorithms
- temporal difference
- adaptive control
- balancing exploration and exploitation
- class of nonlinear systems
- multi agent
- control policy
- state space
- multi agent systems
- control law
- learning algorithm
- closed loop
- optimal policy
- sufficient conditions
- particle swarm optimization
- dynamic programming