تقرير
Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing
| العنوان: | Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing |
|---|---|
| المؤلفون: | Mckinstry, Jeffrey L, Barch, Davis R., Bablani, Deepika, Debole, Michael V., Esser, Steven K., Kusnitz, Jeffrey A., Arthur, John V., Modha, Dharmendra S. |
| سنة النشر: | 2018 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning |
| الوصف: | 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. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1809.09260 |
| رقم الأكسشن: | edsarx.1809.09260 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |