mlsanityData to 14 Oct 2026

HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation

arXiv 2606.30966 ↗First posted 29 Jun 2026cs.AI cs.LO cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor; (2) expressiveness to specify objectives and constraints, and (3) the ability to define tactics to achieve objectives. However, these benefits remain largely unexplored in the context of Multi-Agent Reinforcement Learning (MARL). This paper introduces HyPOLE, a novel framework for MARL under partial observability, where learning is guided by the expressive power of the so-called hyperproperties and, in particular, the temporal logic HyperLTL. We integrate Centralized Training for Decentralized Execution (CTDE) techniques with HyPOLE to synthesize decentralized policies, and our evaluation on SMAC, MessySMAC, and WildFire benchmark demonstrates clear advantages over baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 29 Jun 2026.

Builds on

23 of 36 references.

References · 23

  1. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  2. 2019The StarCraft Multi-Agent Challengecited by 597
  3. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  4. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
  5. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  6. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  7. 2018Logically-Constrained Reinforcement Learningcited by 51
  8. 2020Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulascited by 36
  9. 2019Transfer of Temporal Logic Formulas in Reinforcement Learningcited by 31
  10. 2021Multi-Agent Reinforcement Learning with Temporal Logic Specificationscited by 27
  11. 2019Modular Deep Reinforcement Learning with Temporal Logic Specificationscited by 25
  12. 2014Temporal Logics for Hyperpropertiescited by 19
11 more
  1. 2024Reinforcement Learning with LTL and ω-Regular Objectives via Optimality-Preserving Translation to Average Rewardscited by 14
  2. 2020Stochastic Finite State Control of POMDPs with LTL Specificationscited by 11
  3. 2020Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learningcited by 9
  4. 2022Specification-Guided Learning of Nash Equilibria with High Social Welfarecited by 8
  5. 2023Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observabilitycited by 8
  6. 2021Reinforcement Learning with Temporal Logic Constraints for Partially-Observable Markov Decision Processescited by 4
  7. 2024Non-Deterministic Planning for Hyperproperty Verificationcited by 4
  8. 2024Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shapingcited by 4
  9. 2022Logic-based Reward Shaping for Multi-Agent Reinforcement Learningcited by 3
  10. 2020Barrier Functions for Multiagent-POMDPs with DTL Specificationscited by 2
  11. 2025HypRL: Reinforcement Learning of Control Policies for Hyperpropertiescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information
  2. 2026Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning
  3. 2026KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning
  4. 2026Probing Dec-POMDP Reasoning in Cooperative MARL
  5. 2025Remembering the Markov Property in Cooperative MARL
  6. 2025HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
  7. 2025Automating the Refinement of Reinforcement Learning Specifications
  8. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use