M2DQN: A Robust Method for Accelerating Deep Q-learning Network.
Zhe ZhangYukun ZouJunjie LaiQing XuPublished in: ICMLC (2023)
Keyphrases
- reinforcement learning
- distributed network
- multi agent
- network model
- network size
- cooperative
- computer networks
- network traffic
- peer to peer
- network structure
- neural network
- network architecture
- dynamic environments
- learning algorithm
- intrusion detection
- state space
- wireless sensor networks
- communication cost
- social networks
- network management
- machine learning
- data sets
- multi agent reinforcement learning