Partially Observable Multi-Agent Deep Reinforcement Learning for Cognitive Resource Management.
Ning YangHaijun ZhangRandall BerryPublished in: GLOBECOM (2020)
Keyphrases
- resource management
- partially observable
- reinforcement learning
- multi agent
- intelligent agents
- state space
- partial observability
- management system
- markov decision processes
- resource allocation
- hidden state
- function approximation
- partially observable domains
- grid computing
- reinforcement learning algorithms
- markov decision problems
- partial observations
- quality of service
- learning algorithm
- action models
- single agent
- reward function
- machine learning
- temporal difference
- model free
- decision problems
- multi agent systems
- partially observable environments
- decision making
- dynamic programming
- optimal policy
- partially observable markov decision processes
- cooperative
- transfer learning
- real time
- partially observable markov decision process
- optimal control
- orders of magnitude
- multiple agents
- computational intelligence
- grid systems
- computational complexity