Feedback controller parameterizations for reinforcement learning
Reinforcement Learning offers a very general framework for learning controllers, but its effectiveness is closely tied to the controller parameterization used. Especially when learning feedback controllers for weakly stable systems, ineffective parameterizations can result in unstable controllers an...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2011
|
| Online Access: | http://hdl.handle.net/1721.1/67496 https://orcid.org/0000-0002-8712-7092 |
| Summary: | Reinforcement Learning offers a very general framework for learning controllers, but its effectiveness is closely tied to the controller parameterization used. Especially when learning feedback controllers for weakly stable systems, ineffective parameterizations can result in unstable controllers and poor performance both in terms of learning convergence and in the cost of the resulting policy. In this paper we explore four linear controller parameterizations in the context of REINFORCE, applying them to the control of a reaching task with a linearized flexible manipulator. We find that some natural but naive parameterizations perform very poorly, while the Youla Parameterization (a popular parameterization from the controls literature) offers a number of robustness and performance advantages. |
|---|