Q-Learning-Based Voltage-Swing Tuning and Compensation for 2.5-D Memory-Logic Integration.
Dongjun XuNingmei YuHantao HuangSai Manoj Pudukotai DinakarraoHao YuPublished in: IEEE Des. Test (2018)
Keyphrases
- memory usage
- multi agent
- data integration
- reinforcement learning
- logic programming
- transmission line
- state space
- cooperative
- electrical power
- function approximation
- stochastic approximation
- high voltage
- main memory
- modal logic
- temporal difference learning
- multi valued
- reinforcement learning algorithms
- optimal policy
- model free
- neural network
- power system
- power supply
- data structure
- random access memory
- database systems
- learning algorithm