Internally Driven Q-learning - Convergence and Generalization Results
Alonso, E. 
ORCID: 0000-0002-3306-695X, Mondragon, E. ORCID: 0000-0003-4180-1261 & Kjaell-Ohlsson, N. (2012).
Internally Driven Q-learning - Convergence and Generalization Results.
In: Filipe, J. & Fred, A. (Eds.),
Proceedings of the 4th International Conference on Agents and Artificial Intelligence.
4th International Conference on Agents and Artificial Intelligence, 6-8 Feb 2012, Algarve, Portugal.
doi: 10.5220/0003736404910494
Abstract
We present an approach to solving the reinforcement learning problem in which agents are provided with internal drives against which they evaluate the value of the states according to a similarity function. We extend Q-learning by substituting internally driven values for ad hoc rewards. The resulting algorithm, Internally Driven Q-learning (IDQ-learning), is experimentally proved to convergence to optimality and to generalize well. These results are preliminary yet encouraging: IDQ-learning is more psychologically plausible than Q-learning, and it devolves control and thus autonomy to agents that are otherwise at the mercy of the environment (i.e., of the designer).
| Publication Type: | Conference or Workshop Item (Paper) |
|---|---|
| Publisher Keywords: | Q-learning, IDQ-learning, Internal Drives, Convergence, Generalization |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Departments: | School of Science & Technology > Computer Science |
Download (150kB) | Preview
Export
Downloads
Downloads per month over past year
Metadata
MetadataActions (login required)
Admin Login