Learning to Advertise with Adaptive Exposure via Constrained Two-Level Reinforcement Learning.
Weixun WangJunqi JinJianye HaoChunjie ChenChuan YuWeinan ZhangJun WangYixi WangHan LiJian XuKun GaiPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- eligibility traces
- online learning
- learning capabilities
- learning systems
- autonomous learning
- learning tasks
- adaptive control
- learning problems
- multi agent
- actor critic
- evolutionary learning
- robot control
- reinforcement learning algorithms
- dynamic programming
- learning experience
- supervised learning
- semi supervised
- state space