Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability

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 concurrently-exploring teammates. Approaches that learn specialized polic...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-07
Main Authors: Shayegan Omidshafiei, Pazis, Jason, Amato, Christopher, How, Jonathan P, Vian, John
Format: Article
Language:English
Subjects:
Distillation
Machine learning
Multiagent systems
Observability (systems)
Policies
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face 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.
ISSN:2331-8422