Web: http://arxiv.org/abs/2201.10803

Jan. 27, 2022, 2:10 a.m. | Hon Tik Tse, Ho-fung Leung

cs.LG updates on arXiv.org arxiv.org

Multi-agent reinforcement learning (MARL) can model many real world
applications. However, many MARL approaches rely on epsilon greedy for
exploration, which may discourage visiting advantageous states in hard
scenarios. In this paper, we propose a new approach QMIX(SEG) for tackling
MARL. It makes use of the value function factorization method QMIX to train
per-agent policies and a novel Semantic Epsilon Greedy (SEG) exploration
strategy. SEG is a simple extension to the conventional epsilon greedy
exploration strategy, yet it is experimentally …

arxiv exploration learning reinforcement learning semantic strategy

More from arxiv.org / cs.LG updates on arXiv.org

Senior Data Analyst

@ Fanatics Inc | Remote - New York

Data Engineer - Search

@ Cytora | United Kingdom - Remote

Product Manager, Technical - Data Infrastructure and Streaming

@ Nubank | Berlin

Postdoctoral Fellow: ML for autonomous materials discovery

@ Lawrence Berkeley National Lab | Berkeley, CA

Principal Data Scientist

@ Zuora | Remote

Data Engineer

@ Veeva Systems | Pennsylvania - Fort Washington