Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning.
Yufei KuangXijun LiJie WangFangzhou ZhuMeng LuZhihai WangJia ZengHouqiang LiYongdong ZhangFeng WuPublished in: CoRR (2023)
Keyphrases
- linear programming
- reinforcement learning
- linear program
- dynamic programming
- state space
- real life
- markov decision problems
- reinforcement learning algorithms
- np hard
- small scale
- function approximation
- database
- model free
- primal dual
- stochastic approximation
- machine learning
- policy iteration
- nonlinear programming
- web scale
- robotic control
- reward function
- constraint propagation
- transfer learning
- optimization problems
- least squares
- support vector
- real world