RT Book, Section
T1 Applying game-learning environments to power capping scenarios via reinforcement learning
A1 Hernández Aguado, Pablo
A1 Costero Valero, Luis María
A1 Olcoz Herrero, Katzalin
A1 Igual Peña, Francisco Daniel
AB Research in deep learning for video game playing has received much attention and provided very relevant results in the last years. Frameworks and libraries have been developed to ease game playing research leveraging Reinforcement Learning techniques. In this paper, we propose to use two of them (RLLIB and GYM) in a very different scenario, such as learning to apply resource management policies in a multi-core server, specifically, we leverage the facilities of both frameworks coupled to derive policies for power-capping. Using RLlib and Gym enables implementing different resource management policies in a simple and fast way and, as they are based on neural networks, guarantees the efficiency in the solution, and the use of hardware accelerators for both training and inference. The results demonstrate that game-learning environments provide an effective support to cast a completely different scenario, and open new research avenues in the field of resource management using reinforcement learning techniques with minimal development effort.
PB Springer international Publishing
SN 978-3-031-14598-8
YR 2022
FD 2022-08-05
LK https://hdl.handle.net/20.500.14352/2494
UL https://hdl.handle.net/20.500.14352/2494
LA eng
NO © Conference on Cloud Computing, Big Data and Emerging Topics (10. 2022. La Plata, Argentina)ISSN 1865-0929This work was supported by the EU (FEDER) and Spanish MINECO (RTI2018-093684-B-I00), and Comunidad de Madrid under the Multiannual Agreement with Complutense University in the line Program to Stimulate Research for Young Doctors in the context of the V PRICIT under projects PR65/19-22445 and CM S2018/TCS-4423.
NO Ministerio de Ciencia e innovación (MICINN) / FEDER
NO Comunidad de Madrid
NO Universidad Complutense de Madrid
DS Docta Complutense
RD 1 may 2024