Reinforcement learning in feedback control
Roland Hafner, Martin Riedmiller · Machine Learning · 2011
Cited by 214 works. doi:10.1007/s10994-011-5235-x Open-access PDF
Authors
References
- Dynamic Programming
- Applied Nonlinear Control
- System Identification: Theory for the User
- Learning from Delayed Rewards
- System identification—Theory for the user
- A direct adaptive method for faster backpropagation learning: the RPROP algorithm
- Practical issues in temporal difference learning
- Technical Note: Q-Learning
- Dynamic System Identification - Experiment Design and Data Analysis
- Advances in Neural Information Processing Systems 7