Towards Efficient Task Offloading at the Edge Based on Meta-Reinforcement Learning with Hybrid Action Space.
Zhao YangYuxiang DengTing WangHaibin CaiPublished in: ICC (2023)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- continuous state
- state and action spaces
- real valued
- continuous state spaces
- function approximation
- reinforcement learning methods
- domain independent
- optimal policy
- dynamic programming
- cooperative
- heuristic search
- mobile robot
- action selection
- stochastic processes
- state action
- bayesian networks