Provably efficient learning with typed parametric models
To quickly achieve good performance, reinforcement-learning algorithms for acting in large continuous-valued domains must use a representation that is both sufficiently powerful to capture important domain characteristics, and yet simultaneously allows generalization, or sharing, among experiences....
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Journal of Machine Learning Research
2010
|
| Online Access: | http://hdl.handle.net/1721.1/60042 https://orcid.org/0000-0002-8293-0492 |