LoopTune: Optimizing Tensor Computations with Reinforcement Learning.
Dejan GrubisicBram WastiChris CumminsJohn M. Mellor-CrummeyAleksandar ZlateskiPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- high order
- reinforcement learning algorithms
- exploration exploitation tradeoff
- optimal policy
- state space
- dimensionality reduction
- model free
- tensor space
- machine learning
- supervised learning
- markov decision processes
- learning process
- higher order
- multi agent
- optimal control
- action selection
- genetic algorithm
- markov decision process
- policy search
- robotic control