Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
This addresses the problem of scalable and practical multi-agent learning in real-world settings with partial observability and multiple tasks, though it is incremental as it builds on existing multi-agent and multi-task methods.
The paper tackles the challenge of multi-agent reinforcement learning under partial observability and multiple tasks, where agents cannot observe task identities, by introducing a decentralized single-task learning method and distilling policies into a unified one, achieving robust performance across tasks without task identity.
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.