Reward based Hebbian Learning in Direct Feedback Alignment (Student Abstract)

Authors

  • Ashlesha Akella School of Computer Science, University of Technology Sydney, Australia
  • Sai Kalyan Ranga Singanamalla School of Computer Science, University of Technology Sydney, Australia
  • Chin-Teng Lin School of Computer Science, University of Technology Sydney, Australia Center for Artificial Intelligence, University of Technology Sydney, Australia

Keywords:

Hebbian Learning, Direct Feedback Alignment, Reinforcement Learning

Abstract

Imparting biological realism during the learning process is gaining attention towards producing computationally efficient algorithms without compromising the performance. Feedback alignment and mirror neuron concept are two such approaches where the feedback weight remains static in the former and update via Hebbian learning in the later. Though these approaches have proven to work efficiently for supervised learning, it remained unknown if the same can be applicable to reinforcement learning applications. Therefore, this study introduces RHebb-DFA where the reward-based Hebbian learning is used to update feedback weights in direct feedback alignment mode. This approach is validated on various Atari games and obtained equivalent performance in comparison with DDQN.

Downloads

Published

2021-05-18

How to Cite

Akella, A., Singanamalla, S. K. R., & Lin, C.-T. (2021). Reward based Hebbian Learning in Direct Feedback Alignment (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15749-15750. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17871

Issue

Section

AAAI Student Abstract and Poster Program