Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing
Machine Learning
2018-09-26 v1 Neural and Evolutionary Computing
Machine Learning
Abstract
Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in the discrete action ATARI domain, we demonstrate, for the first time, that low precision policy distillation from a high precision network provides a principled, practical way to train an RL agent. As an application, on 10 different ATARI games, we demonstrate real-time end-to-end game playing on low-power neuromorphic hardware by converting a sequence of game frames into discrete actions.
Keywords
Cite
@article{arxiv.1809.09260,
title = {Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing},
author = {Jeffrey L Mckinstry and Davis R. Barch and Deepika Bablani and Michael V. Debole and Steven K. Esser and Jeffrey A. Kusnitz and John V. Arthur and Dharmendra S. Modha},
journal= {arXiv preprint arXiv:1809.09260},
year = {2018}
}