Accelerating deep reinforcement learning via knowledge-guided policy network.
Yuanqiang YuPeng ZhangKai ZhaoYan ZhengJianye HaoPublished in: Auton. Agents Multi Agent Syst. (2023)
Keyphrases
- reinforcement learning
- optimal policy
- knowledge representation
- wireless sensor networks
- policy search
- markov decision processes
- approximate dynamic programming
- complex domains
- action selection
- computer networks
- network traffic
- knowledge base
- domain experts
- knowledge management
- network structure
- state space
- network model
- knowledge discovery
- domain knowledge
- function approximators
- control policies
- learning process
- expert systems
- reinforcement learning problems