The Small Loop Problem: A Challenge for Artificial Emergent Cognition
We propose the Small Loop Problem as a challenge for biologically inspired cognitive architectures. This challenge consists of designing an agent that would autonomously organize its behavior through interaction with an initially unknown environment that offers basic sequential and spatial regularities. The Small Loop Problem demonstrates four principles that we consider crucial to the implementation of emergent cognition: environment-agnosticism, self-motivation, sequential regularity learning, and spatial regularity learning. While this problem is still unsolved, we report partial solutions that suggest that its resolution is realistic.
KeywordsSelf-motivation decision process early-stage cognition
Unable to display preview. Download preview PDF.
- 1.Aström, K.: Optimal control of Markov processes with incomplete state information. Journal of Mathematical Analysis and Applications (10), 174–205 (1965)Google Scholar
- 6.Gay, S., Georgeon, O.L., Kim, J.W.: Implementing spatial awareness in an environment-agnostic agent. In: Proceedings of BRIMS 2012, 21st Annual Conference on Behavior Representation in Modeling and Simulation, Amelia Island, Florida, pp. 62–69 (2012)Google Scholar
- 8.Georgeon, O.L., Sakellariou, I.: Designing environment-agnostic agents. In: Proceedings of ALA 2012, Adaptive Learning Agents Workshop at AAMAS 2012, 11th International Conference on Autonomous Agents and Multiagent Systems, Valencia, Spain, pp. 25–32 (2012)Google Scholar
- 12.Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)Google Scholar