Search Results for author:
Found 7 papers, 4 papers with code
Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning
We evaluate our approach with three state-of-the-art DRL algorithms and find that differential image encoding reduces the memory footprint by as much as 14. 2x and 16. 7x across tasks from the Atari 2600 benchmark and the DeepMind Control Suite (DMC) respectively.
Datasheets for Machine Learning Sensors: Towards Transparency, Auditability, and Responsibility for Intelligent Sensing
Machine learning (ML) sensors are enabling intelligence at the edge by empowering end-users with greater control over their data.
Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers
This article discusses both the potential of these TinyML applications to address critical sustainability challenges, as well as the environmental footprint of this emerging technology.
Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion
Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing complex robotic behaviors.
Machine Learning Sensors
Machine learning sensors represent a paradigm shift for the future of embedded machine learning applications.
Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots
Machine learning (ML) has become a pervasive tool across computing systems.
Widening Access to Applied Machine Learning with TinyML
Broadening access to both computational and educational resources is critical to diffusing machine-learning (ML) innovation.
