Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: We study the problem of learning multi-task, multi-agent policies for
cooperative, temporal objectives, under centralized training, decentralized
execution. In this setting, using automata to represent tasks enables the
decomposition of complex tasks into simpler sub-tasks that can be assigned to
agents. However, existing approaches remain sample-inefficient and are limited
to the single-task case. In this work, we present Automata-Conditioned
Cooperative Multi-Agent Reinforcement Learning (ACC-MARL), a framework for
learning task-conditioned, decentralized team policies. We identify the main
challenges to ACC-MARL's feasibility in practice, propose solutions, and prove
the correctness of our approach. We further show that the value functions of
learned policies can be used to assign tasks optimally at test time.
Experiments show emergent task-aware, multi-step coordination among agents,
e.g., pressing a button to unlock a door, holding the door, and
short-circuiting tasks.
Key Contributions
ACC-MARL is a novel framework for learning task-conditioned, decentralized cooperative multi-agent policies under centralized training. It leverages automata to represent complex temporal objectives, enabling task decomposition and assignment, and addresses sample inefficiency. The framework allows for emergent task-aware coordination and optimal task assignment at test time.
Business Value
Enables more sophisticated coordination and task execution in multi-robot systems or distributed autonomous agents, leading to increased efficiency and capability in logistics, manufacturing, and exploration.