PLATO: Pointer Learner for Agent and Task Openness

2026-07-27

AI Summary

This work addresses the challenge of unbounded state and action spaces in open multi-agent systems, where both agents and tasks dynamically enter and exit. To tackle this, the paper proposes PLATO, a novel framework that, within the centralized training with decentralized execution paradigm, is the first to jointly model the dual openness of agents and tasks without requiring predefined boundaries or masking mechanisms. The problem is formally cast as a Task-Agent-Open Markov Game (TaAgO-MG). PLATO integrates a pointer network actor, a graph neural network critic, multi-agent proximal policy optimization, and dynamic graph encoding. Evaluated in the MOASEI wildfire suppression environment, PLATO significantly outperforms existing methods, demonstrating superior performance and strong zero-shot generalization capabilities.

Abstract

Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openness (AO) and task openness (TO), poses a fundamental challenge to multi-agent reinforcement learning (MARL), which typically assumes fixed state and action spaces. Existing methods address openness only partially: padding and masking approaches introduce artificial bounds, while recent graph-based or hypergraph methods handle one dimension of openness but still depend on restrictive assumptions. In this paper, we introduce Pointer Learner for Agent and Task Openness (PLATO), a pointer-network-based actor combined with a centralized graph neural network (GNN) critic, trained with multi-agent proximal policy optimization under a centralized training and decentralized execution paradigm. Our pointer-based actor outputs distributions directly over the current task set. This directly supports changing action spaces without masking or retraining. Our GNN critic encodes agent-task interactions as a graph that changes shape with task and agent composition. Together, these components consider AO and TO without the boundedness of existing approaches. We formalize PLATO in a Task-and-Agent-Open Markov Game (TaAgO-MG), extending prior task-open formulations, and prove it is well-defined over the resulting unbounded state and action spaces. We evaluate PLATO with the Methods for Open Agent Systems Evaluation Initiative (MOASEI) wildfire suppression domain, an environment designed for open multi-agent system evaluation, and we demonstrate strong performance and more consistent zero-shot generalization than state-of-the-art baselines in OASYS.

Problem

• open agent systems
• agent openness
• task openness
• multi-agent reinforcement learning
• unbounded action spaces

Innovation

• Pointer Network
• Graph Neural Network
• Open Agent Systems
• Task Openness
• Multi-Agent Reinforcement Learning