Skip to main content Accessibility help

Maximal mutual information, not minimal entropy, for escaping the “Dark Room”

  • Daniel Ying-Jeh Little (a1) and Friedrich Tobias Sommer (a1)


A behavioral drive directed solely at minimizing prediction error would cause an agent to seek out states of unchanging, and thus easily predictable, sensory inputs (such as a dark room). The default to an evolutionarily encoded prior to avoid such untenable behaviors is unsatisfying. We suggest an alternate information theoretic interpretation to address this dilemma.



Hide All
Ay, N., Bertschinger, N., Der, R., Güttler, F. & Olbrich, E. (2008) Predictive information and explorative behavior of autonomous robots. The European Physical Journal B – Condensed Matter and Complex Systems 63(3):32939.
Crutchfield, J. P. & Young, K. (1989) Inferring statistical complexity. Physical Review Letters 63:105108.
Friston, K. & Stephan, K. (2007) Free energy and the brain. Synthese 159(3):417–58.
Little, D. Y. & Sommer, F. T. (2011) Learning in embodied action-perception loops through exploration. Online Publication arXive:1112.1125.
Still, S. (2009) Information-theoretic approach to interactive learning. Europhysics Letters 85:28005.
Tishby, N., Pereira, F. C. & Bialek, W. (1999) The information bottleneck method. In: Proceedings of the 37th Allerton Conference on Communication, Control, and Computing, ed. Hajek, B. & Sreenivas, R. S., pp. 368–77. University of Illinois Press.


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed