Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion
Lev Grossman,Brian Plancher,Lev Grossman,Brian Plancher
Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing complex robotic behaviors. But training DRL models is incredibly compute and memory intensive, requiring large training datasets and replay buffers to achieve performant results. This poses a challenge for the next generation of field robots that will need to learn on the edge to adapt to their environment. In thi...
