Reinforcement Learning for Thermal-aware Many-core Task Allocation.
Shiting (Justin) LuRussell TessierWayne P. BurlesonPublished in: ACM Great Lakes Symposium on VLSI (2015)
Keyphrases
- reinforcement learning
- infrared
- model free
- function approximation
- multi agent systems
- multi agent
- multiagent systems
- state space
- machine learning
- temporal difference
- markov decision processes
- optimal policy
- learning process
- learning algorithm
- supervised learning
- face recognition
- learning agents
- multi robot
- coalition formation
- transition model
- policy search
- stochastic approximation
- neural network
- action space
- thermal infrared
- partially observable
- optimal control
- learning problems
- transfer learning
- dynamic programming
- cooperative
- e learning