A Dual-Critic Deep Deterministic Policy Gradient Approach for Task Offloading in Edge-Fog-Cloud Environment.
Moshira A. EbrahimGamal A. EbrahimHoda K. MohamedPublished in: ICCA (2023)
Keyphrases
- policy gradient
- actor critic
- function approximation
- reinforcement learning
- optimal control
- gradient method
- reinforcement learning algorithms
- approximation methods
- model free reinforcement learning
- partially observable markov decision processes
- variance reduction
- reinforcement learning methods
- average reward
- temporal difference
- monte carlo
- state space
- dynamic programming
- natural actor critic
- machine learning