Deep decentralized multi-task multi-agent reinforcement learning under partial observability
Name
1703.06182.pdf
Description
Accepted version
Size
2.99 MB
Format
Adobe PDF
Checksum (MD5)
1796a23bda3c37997dd5dc8fd53f3868
Author(s)
How, Jonathan
Date Issued
2017
Citation
How, Jonathan. 2017. "Deep decentralized multi-task multi-agent reinforcement learning under partial observability."
Version
Author's final manuscript
Abstract
Copyright © 2017 by the author(s). Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrentlyexploring teammates. Approaches that learn specialized policies for individual tasks facc problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of multi-task multi-agent reinforcement learning under partial observability. We introduce a decentralized single-task learning approach that is robust to concurrent interactions of teammates, and present an approach for distilling single-task policies into a unified policy that performs well across multiple related tasks, without explicit provision of task identity.
MIT Department
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://dl.acm.org/doi/10.5555/3305890.3305958
