HARL: Hierarchical Adaptive Reinforcement Learning Based Auto Scheduler for Neural Networks

no code implementations • 21 Nov 2022 • Zining Zhang, Bingsheng He, Zhenjie Zhang

However, due to the gigantic search space and lack of intelligent search guidance, current auto-schedulers require hours to days of tuning time to find the best-performing tensor program for the entire neural network.

reinforcement-learning Reinforcement Learning (RL)