EUVIMEDEUVIMED entdecken
Crossref

Multiagent Reinforcement Learning: Rollout and Policy Iteration for POMDP With Application to Multirobot Problems

Sushmita Bhattacharya, Siva Kailas, Sahil Badyal, Stephanie Gil, Dimitri Bertsekas

IEEE Transactions on Robotics · 2024 · 40 · 2003-2023

DOI: 10.1109/tro.2023.3347128 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2024. Verfasst von Sushmita Bhattacharya und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: ONR Young Investigators, Sloan Research Fellowship, NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this article, we consider the computational and communication challenges of partially observable multiagent sequential decision-making problems. We present algorithms that simultaneously or sequentially optimize the agents' controls by using multistep lookahead, truncated rollout with a known base policy, and a terminal cost function approximation. In particular: 1) we consider multiagent rollout algorithms that dramatically reduce required computation while preserving the key policy improvement property of the standard rollout method. We improve our multiagent rollout policy by incorporating it in an offline approximate policy iteration scheme, and we apply an additional “online play” scheme enhancing offline approximation architectures; 2) we consider the imperfect communication case and provide various extensions to our rollout methods to deal with this case; and 3) we demonstrate the performance of our methods in extensive simulations by applying our method to a challenging partially observable multiagent sequential repair problem (state space size $10^{37}$ and control space size $10^{7}$). Our extensive simulations demonstrate that our methods produce better policies for large and complex multiagent problems in comparison with existing methods, including POMCP, MADDPG, and work well where other methods fail to scale up.

Förderung

  • ONR Young Investigators
  • Sloan Research Fellowship
  • NSF
  • Apple Scholars in AI/ML Ph.D. Fellowship Program

Zitieren

APA

Bhattacharya, S., Kailas, S., Badyal, S., Gil, S., & Bertsekas, D. (2024). Multiagent Reinforcement Learning: Rollout and Policy Iteration for POMDP With Application to Multirobot Problems. IEEE Transactions on Robotics, 40, 2003-2023. https://doi.org/10.1109/tro.2023.3347128

Vancouver

Bhattacharya S, Kailas S, Badyal S, Gil S, Bertsekas D. Multiagent Reinforcement Learning: Rollout and Policy Iteration for POMDP With Application to Multirobot Problems. IEEE Transactions on Robotics. 2024;40:2003-2023. doi:10.1109/tro.2023.3347128

BibTeX
@article{Bhattacharya2024,
  author = {Bhattacharya, Sushmita and Kailas, Siva and Badyal, Sahil and Gil, Stephanie and Bertsekas, Dimitri},
  title = {Multiagent Reinforcement Learning: Rollout and Policy Iteration for POMDP With Application to Multirobot Problems},
  journal = {IEEE Transactions on Robotics},
  year = {2024},
  volume = {40},
  pages = {2003--2023},
  doi = {10.1109/tro.2023.3347128}
}
Kostenlos starten →