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

TL;DR

This paper addresses the challenge of multi-task multi-agent reinforcement learning under partial observability by proposing a decentralized approach and a policy distillation method that handles multiple tasks without explicit task identities.

Contribution

It introduces a decentralized single-task learning framework and a policy distillation technique for multi-task multi-agent RL under partial observability, overcoming limitations of task-specific policies.

Findings

Decentralized learning is robust to non-stationary multi-agent interactions.

Policy distillation enables multi-task performance without explicit task identities.

The approach improves scalability and applicability in real-world multi-agent systems.

Abstract

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.