Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach.
Changwen ZhangWenli OuyangHao YuanLiming GongYong SunZiao GuoZhichen DongJunchi YanPublished in: ICLR (2024)
Keyphrases
- imitation learning
- reinforcement learning
- reinforcement learning methods
- function approximation
- reinforcement learning algorithms
- machine learning
- multi agent
- model free
- transfer learning
- learning algorithm
- control problems
- robotic systems
- state space
- dynamic programming
- multi modal
- optimal control
- humanoid robot
- supervised learning
- temporal difference
- learning process
- markov decision processes
- learning problems
- optimal policy
- computer vision