Accumulator Based Arbitration Model for both Supervised and Reinforcement Learning Inspired by Prefrontal Cortex
A method that provides an excellent performance by arbitrating multiple modules is important. There are variety of multi-module arbitration methods proposed in various contexts. However, there is yet to be a multi-module arbitration method proposed in reference to structure of animals’ brains. Considering that the animals’ brains achieve general-purpose multi-module arbitration, such function may be achieved by referring to the actual brain. In this paper, with reference to the knowledge of accumulator neurons hypothesized to exist in the prefrontal cortex, we propose an Accumulator Based Arbitration Model (ABAM). By arbitrating multiple modules, ABAM exerts a superior performance in both supervised learning and reinforcement learning task.
KeywordsAccumulator model Ensemble learning Hierarchical architecture Prefrontal cortex
This work was supported by JSPS KAKENHI Grant Number 17J00580.
- 1.Schapire, R.E.: The strength of weak learnability. In: Proceedings of 30th Annual Symposium on Foundations of Computer Science, pp. 28–33. IEEE (1989)Google Scholar
- 2.Freund, Y.: Boosting a weak learning algorithm by majority. In: Proceedings of the Third Annual Workshop on Computational Learning Theory, pp. 202–216 (1990)Google Scholar
- 5.Zhang, X., Povey, D., Khudanpur, S.: A diversity-penalizing ensemble training method for deep learning. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)Google Scholar
- 8.Tessler, C., Givony, S., Zahavy, T., Mankowitz, D.J., Mannor, S.: A deep hierar-chical approach to lifelong learning in minecraft. arXiv preprint (2016). arXiv:1604.07255
- 9.Arulkumaran, K., Dilokthanakul, N., Shanahan, M., Bharath, A.A.: Classifying options for deep reinforcement learning. arXiv preprint (2016). arXiv:1604.08153
- 10.OReilly, R.C., Munakata, Y., Frank, M., Hazy, T., et al.: Computational Cognitive Neuroscience. PediaPress (2012)Google Scholar