Volume 85, Number 2, January 2009
|Number of page(s)||6|
|Section||Interdisciplinary Physics and Related Areas of Science and Technology|
|Published online||30 January 2009|
Information-theoretic approach to interactive learning
University of Hawaii at Manoa, ICS Department - Honolulu, HI 96822, USA
Corresponding author: email@example.com
Accepted: 3 January 2009
The principles of statistical mechanics and information theory play an important role in learning and have inspired both theory and the design of numerous machine learning algorithms. The new aspect in this paper is a focus on integrating feedback from the learner. A quantitative approach to interactive learning and adaptive behavior is proposed, integrating model- and decision-making into one theoretical framework. This paper follows simple principles by requiring that the observer's world model and action policy should result in maximal predictive power at minimal complexity. Classes of optimal action policies and of optimal models are derived from an objective function that reflects this trade-off between prediction and complexity. The resulting optimal models then summarize, at different levels of abstraction, the process's causal organization in the presence of the learner's actions. A fundamental consequence of the proposed principle is that the learner's optimal action policies balance exploration and control as an emerging property. Interestingly, the explorative component is present in the absence of policy randomness, i.e. in the optimal deterministic behavior. This is a direct result of requiring maximal predictive power in the presence of feedback.
PACS: 89.70.-a – Information and communication theory / 05.65.+b – Self-organized systems / 05.45.Tp – Time series analysis
© EPLA, 2009
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.