For deep neural network accelerators, memory movement is both energetically expensive and can bound computation. Therefore, optimal mapping of tensors to memory hierarchies is critical to performance. The growing complexity of neural networks calls for automated memory mapping instead of manual heuristic approaches; yet the search space of neural network computational graphs have previously been prohibitively large. We introduce Evolutionary Graph Reinforcement Learning (EGRL), a method designed for large search spaces, that combines graph neural networks, reinforcement learning, and evolutionary search. A set of fast, stateless policies guide the evolutionary search to improve its sample-efficiency. We train and validate our approach directly on the Intel NNP-I chip for inference. EGRL outperforms policy-gradient, evolutionary search and dynamic programming baselines on BERT, ResNet-101 and ResNet-50. We additionally achieve 28-78\% speed-up compared to the native NNP-I compiler on all three workloads.
Optimizing Electric Vehicle Charging Station Placement Using Reinforcement Learning and Agent-Based Simulations
organization= Center for Environmental Intelligence, VinUniversity , city= Hanoi , country= Vietnam；organization= College of Engineering \& Computer Science, VinUniversity , city= Hanoi , country= Vietnam
Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning
University of Ottawa（渥太华大学）；National Research Council of Canada（加拿大国家研究委员会）；University of Ontario Institute of Technology（安大略理工大学）；University of Victoria（维多利亚大学）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）；Molecular Foundry, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室分子铸造厂）
Department of EECS, UC Berkeley, CA, USA（UC伯克利电子工程与计算机科学系）；SambaNova Systems Inc., Palo Alto, CA, USA（SambaNova Systems公司）；Computer Science Department, Stanford University, CA, USA（斯坦福大学计算机科学系）
Optimizing Search Advertising Strategies: Integrating Reinforcement Learning with Generalized Second-Price Auctions for Enhanced Ad Ranking and Bidding
Columbia University（哥伦比亚大学）；University of Michigan（密歇根大学）；University of California, Irvine（加利福尼亚大学尔湾分校）
CNFP: Optimizing Cloud-Native Network Function Placement with Diffusion Models on the Cloud Continuum
atlanTTic - I&C Lab - Universidade de Vigo（atlanTTic - I&C实验室 - 维戈大学）；Centro Tecnolóxico de Telecomunicacións de Galicia (GRADIANT)（加利西亚电信技术中心（GRADIANT））
X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning
Faculty of Engineering, Yokohama National University（Yokohama国立大学工学部）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）
