A Reinforcement Learning Approach for D2D-Assisted Cache-Enabled HetNets.
Jie TangHengbin TangNan ZhaoKanapathippillai CumananShunqing ZhangYongjin ZhouPublished in: GLOBECOM (2019)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- pose estimation
- markov decision processes
- reinforcement learning algorithms
- prefetching
- image registration
- hit rate
- query processing
- optimal policy
- data access
- optimal control
- state space
- cache management
- multi agent reinforcement learning
- database
- multiple queries
- embedded processors
- temporal difference learning
- learning classifier systems
- response time
- data sets