Abstract
Solving in an efficient manner many different optimal control tasks within the same underlying environment requires decomposing the environment into its computationally elemental fragments. We suggest how to find fragmentations using unsupervised, mixtures model, learning methods on data derived from optimal value functions for multiple tasks, and show that these fragmentations are in accord with observable structures in the environments. Further, we present evidence that such fragments can be of use in a practical reinforcement learning context, by facilitating online, actor-critic learning of multiple goals MDPs.
Original language | English (US) |
---|---|
Pages (from-to) | 325-346 |
Number of pages | 22 |
Journal | Machine Learning |
Volume | 49 |
Issue number | 2-3 |
DOIs | |
State | Published - Nov 2002 |
Externally published | Yes |
Keywords
- Density estimation
- Dynamic programming
- Mixture models
- Reinforcement learning
- Unsupervised learning
- Value functions
ASJC Scopus subject areas
- Software
- Artificial Intelligence