Target-independent XLA optimization using Reinforcement Learning.
Milan GanaiHaichen LiTheodore EnnsYida WangRandy HuangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimization problems
- optimization method
- function approximation
- optimization algorithm
- optimal policy
- global optimization
- multi agent
- supervised learning
- dynamic programming
- learning process
- data sets
- combinatorial optimization
- optimization methods
- constrained optimization
- target tracking
- previously learned
- multi agent reinforcement learning