mlsanityData to 14 Oct 2026

PLATO: Pointer Learner for Agent and Task Openness

arXiv 2607.25082 ↗First posted 27 Jul 2026cs.AI cs.MAcited by 0

On the map: Deep reinforcement learning methods → Multi-agent reinforcement learning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multi-agent reinforcement learning, one of 15 directions in Deep reinforcement learning methods. Builds on 21 of its 38 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

21 of 38 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  7. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  8. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  9. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  10. 2015Pointer Networkscited by 895
  11. 2017Deep Reinforcement Learning that Matterscited by 754
  12. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
9 more
  1. 2018Graph Convolutional Reinforcement Learningcited by 152
  2. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  3. 2020Towards Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 37
  4. 2019Scalable Decision-Theoretic Planning in Open and Typed Multiagent Systemscited by 7
  5. 2019Multi-task Learning and Catastrophic Forgetting in Continual Reinforcement Learningcited by 5
  6. 2019Computing Maximum Matchings in Temporal Graphscited by 3
  7. 2025Inaugural MOASEI Competition at AAMAS'2025: A Technical Reportcited by 3
  8. 2025Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systemscited by 2
  9. 2013Modularity and Openness in Modeling Multi-Agent Systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  2. 2026SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
  3. 2026Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
  4. 2025Graph-Enhanced Policy Optimization in LLM Agent Training
  5. 2026Cross-Benchmark Transfer from RL on Agentic Coding Tasks
  6. 2026OpenTinker: Separating Concerns in Agentic Reinforcement Learning
  7. 2024Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
  8. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization