HAT-DRL: Hotspot-Aware Task Mapping for Lifetime Improvement of Multicore System using Deep Reinforcement Learning.
Jinwei ZhangSheriff SadiqbatchaYuanqi GaoMichael O'DeaNanpeng YuSheldon X.-D. TanPublished in: MLCAD (2020)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- dynamic programming
- state space
- multi agent reinforcement learning
- multi agent
- database
- energy consumption
- transfer learning
- model free
- optimal policy
- life span
- early warning
- reinforcement learning algorithms
- optimal control
- learning tasks
- computer systems
- significant improvement
- machine learning
- neural network