Display Publications by [Year] [Type] [Topic]
Rapid adaptation to dynamically change one`s policy based on a singular observation is a complex problem. This is especially difficult in multiagent systems where the global behavior emerges from inter-agent interactions. In this paper, we introduce a memory-based learning framework called Distributed Modular Memory Unit (DMMU) that enables rapid and adaptive decision making. In DMMU, a shared external memory is selectively accessed by agents acting asynchronously and in parallel. Each agent processes its own stream of sequential information independently while interacting with the shared external memory to identify, retain, and propagate salient information. This enables DMMU to rapidly assimilate task features from a group of distributed agents, consolidate it into a reconfigurable external memory, and use it for one shot multiagent learning. We compare the performance of the DMMU framework on a simulated cybersecurity task with traditional feedforward ensembles, LSTM based agents, and a centralized framework. Results demonstrate that DMMU significantly outperforms the best LSTM based method by a factor of two and exhibits adaptive decision making to effectively solve this complex task.
(unavailable)
@inproceedings{tumer-khadka-aamas18,
author = {S. Khadka and C. Yates and K. Tumer},
title = {A Memory-Based Multiagent Framework for Adaptive Decision Making (Extended Abstract)},
booktitle = {Proceedings of the Seventeeth International Joint Conference on Autonomous Agents and Multiagent Systems},
month = {July},
pages ={},
address = {Stockholm, Sweden},
abstract={Rapid adaptation to dynamically change one`s policy based on a singular observation is a complex problem. This is especially difficult in multiagent systems where the global behavior emerges from inter-agent interactions. In this paper, we introduce a memory-based learning framework called Distributed Modular Memory Unit (DMMU) that enables rapid and adaptive decision making. In DMMU, a shared external memory is selectively accessed by agents acting asynchronously and in parallel. Each agent processes its own stream of sequential information independently while interacting with the shared external memory to identify, retain, and propagate salient information. This enables DMMU to rapidly assimilate task features from a group of distributed agents, consolidate it into a reconfigurable external memory, and use it for one shot multiagent learning. We compare the performance of the DMMU framework on a simulated cybersecurity task with traditional feedforward ensembles, LSTM based agents, and a centralized framework. Results demonstrate that DMMU significantly outperforms the best LSTM based method by a factor of two and exhibits adaptive decision making to effectively solve this complex task.},
bib2html_pubtype = {Refereed Conference Papers},
bib2html_rescat = {Multiagent Systems},
year = {2018}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 16:39:21