Qoe-guaranteed distributed offloading decision via partially observable deep reinforcement learning for edge-enabled Internet of Things.
Jiaxin HouYingbo WuJunpeng CaiZhiwen ZhouPublished in: Neural Comput. Appl. (2023)
Keyphrases
- partially observable
- reinforcement learning
- decision problems
- partial observability
- markov decision processes
- state space
- dynamical systems
- partially observable environments
- partially observable domains
- partial observations
- hidden state
- multi agent
- distributed systems
- optimal policy
- markov decision problems
- infinite horizon
- reinforcement learning algorithms
- function approximation
- belief state
- decision processes
- reward function
- machine learning
- fully observable
- np hard
- decision making
- model free
- action models
- belief space
- inverse reinforcement learning
- learning algorithm
- partially observable markov decision processes
- markov decision process
- finite state
- decision makers
- dynamic programming
- partially observable markov decision process