Characterizing Speed Performance of Multi-Agent Reinforcement Learning
Lists
Only you see this
Abstract
Multi-Agent Reinforcement Learning (MARL) has achieved significant success in large-scale AI systems and big-data applications such as smart grids, surveillance, etc. Existing advancements in MARL algorithms focus on improving the rewards obtained by introducing various mechanisms for inter-agent cooperation. However, these optimizations are usually compute- and memory-intensive, thus leading to suboptimal speed performance in end-to-end training time. In this work, we analyze the speed performance (i.e., latency-bounded throughput) as the key metric in MARL implementations. Specifically, we first introduce a taxonomy of MARL algorithms from an acceleration perspective categorized by (1) training scheme and (2) communication method. Using our taxonomy, we identify three state-of-the-art MARL algorithms - Multi-Agent Deep Deterministic Policy Gradient (MADDPG), Target-oriented Multi-agent Communication and Cooperation (ToM2C), and Networked Multi-agent RL (NeurComm) - as target benchm
BibTeX
@inproceedings{wiggins2023characterizing,
author = {Samuel Wiggins and Yuan Meng and Rajgopal Kannan and Viktor K. Prasanna},
title = {{Characterizing Speed Performance of Multi-Agent Reinforcement Learning}},
booktitle = {DATA},
year = {2023},
doi = {10.5220/0012082200003541},
}Loading related content...