Name
Abstract | ||
|---|---|---|
This paper presents initial results of an investigation of the feasibility of using hierarchical reinforcement learning methods in a restructurable control scenario. In restructurable control the plant's behavior at different times needs to be described by different sets of variables and relationships. Two main problems addressed in this research are: (1) the ability to learn two policy functions (model selection and action selection), and (2) the space complexity for representing such policies in the case of continuous physical systems. |
Year | DOI | Venue |
|---|---|---|
1991 | 10.1016/B978-1-55860-200-7.50065-9 | International Conference on Machine Learning |
Field | DocType | Issue |
Computer science,Physical system,Model selection,Artificial intelligence,Action selection,Machine learning,Reinforcement learning | Conference | 1 |
Citations | PageRank | References |
2 | 0.47 | 1 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mieczyslaw M. Kokar | 1 | 498 | 148.01 |
| Spyros A. Reveliotis | 2 | 140 | 18.02 |