Reinforcement learning with replacing eligibility traces
Machine Learning - Special issue on reinforcement learning
Creating advice-taking reinforcement learners
Machine Learning - Special issue on reinforcement learning
Making large-scale support vector machine learning practical
Advances in kernel methods
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
On integrating apprentice learning and reinforcement learning
On integrating apprentice learning and reinforcement learning
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
A survey of robot learning from demonstration
Robotics and Autonomous Systems
Accelerating reinforcement learning through implicit imitation
Journal of Artificial Intelligence Research
Transfer Learning for Reinforcement Learning Domains: A Survey
The Journal of Machine Learning Research
Hi-index | 0.00 |
This paper introduces a teacher-student framework for reinforcement learning. In this framework, a teacher agent instructs a student agent by suggesting actions the student should take as it learns. However, the teacher may only give such advice a limited number of times. We present several novel algorithms that teachers can use to budget their advice effectively, and we evaluate them in two experimental domains: Mountain Car and Pac-Man. Our results show that the same amount of advice, given at different moments, can have different effects on student learning, and that teachers can significantly affect student learning even when students use different learning methods and state representations.