论文标题
使用稀疏计算的神经网络优化用于强化学习任务
Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations
论文作者
论文摘要
本文提出了一种基于稀疏计算的方法，用于优化用于加强学习（RL）任务的神经网络。该方法结合了两个想法：神经网络修剪和考虑输入数据相关性；仅当更改超过一定阈值时，才能更新神经元。运行神经网络时，它大大减少了乘积的数量。我们测试了不同的RL任务，并减少了乘法数量的20-150x。没有实质性的损失；有时表现甚至有所改善。
This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks. This method combines two ideas: neural network pruning and taking into account input data correlations; it makes it possible to update neuron states only when changes in them exceed a certain threshold. It significantly reduces the number of multiplications when running neural networks. We tested different RL tasks and achieved 20-150x reduction in the number of multiplications. There were no substantial performance losses; sometimes the performance even improved.
