Loading...
Please wait, while we are loading the content...
Similar Documents
An Application of Importance-based Feature Extraction in Reinforcement Learning
| Content Provider | Semantic Scholar |
|---|---|
| Author | Finton, David J. Hu, Yu Hen |
| Copyright Year | 1994 |
| Abstract | |The sparse feedback in reinforcement learning problems makes feature extraction diicult. We present importance-based feature extraction, which guides a bottom-up self-organization of feature detectors according to top-down information as to the importance of the features; we deene importance in terms of the reinforcement values expected as a result of taking diierent actions when a feature is recognized. We illustrate these ideas in terms of the pole-balancing task and a learning system which combines bottom-up tuning with a distributed version of Q-learning; adding importance-based feature extraction to the detector tuning resulted in faster learning. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.cs.wisc.edu/~finton/nnsp94.ps |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Bottom-up proteomics Detectors Equilibrium Feature extraction Q-learning Reinforcement learning Self-organization Sparse matrix Top-down and bottom-up design |
| Content Type | Text |
| Resource Type | Article |
