Quantization in neural network inference refers to the process of mapping high-precision parameters and activations to lower-precision representations, typically using integer or even binary values.
In real applications of Reinforcement Learning (RL), such as robotics, low latency, energy-efficient and high-throughput inference is very desired. The use of sparsity and pruning for optimizing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results