今天主要参与了以下两个workshop:
- Workshop on Methods and Applications of Reinforcement Learning
- AutoML Workshop at PRICAI 2018
比较重要的points记录如下:
- Curriculum Learning
- When training machine learning models, start with easier subtasks and gradually increase the difficulty level of the tasks
- Motivation comes from the observation that humans and animals seem to learn better when trained with a curriculum like a strategy
- Maybe mitigate the issue of reward design
- Link to the paper
- Model-based Search (hyperparameter tunning)
-
Model-based Derivative-free Methods for Optimization
- RACOS
- Yang Yu, Hong Qian, and Yi-Qi Hu. Derivative-Free Optimization via Classification. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI16), Phoenix, AZ, 2016 PDF file
- SRACOS
- Yi-Qi Hu, Hong Qian, and Yang Yu. Sequential classification-based optimization for direct policy search. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI17), San Francisco, CA, 2017. PDF file
- RACOS