An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems
cs.LG, cs.AI, cs.MA
Submitted: 2026-11-02
Updated: 2026-11-12
Comments: 43 pages, Published at NeurIPS 2026
Code: https://github.com/hsvgbkhgbv/axiomatic-rl-naht
License: http://creativecommons.org/licenses/by/4.0/
The gist: Open multi-agent systems, where only a subset of agents are controllable, are central to real-world domains such as smart grids…
Terminology
Abstract
Open multi-agent systems, where only a subset of agents are controllable, are central to real-world domains such as smart grids, yet lack a principled foundation for reinforcement learning algorithm design. We study this setting through n-agent ad hoc teamwork (NAHT), a recent framework for learning in open multi-agent environments. We propose an axiomatic framework that derives value function learning from the Shapley axioms (Efficiency, Symmetry and Linearity), treating them as structural constraints rather than heuristic design choices. This formulation builds on a novel NAHT decomposition, which characterises the fundamental difference between open and fully controllable multi-agent systems, and establishes a cooperative game-theoretic foundation for learning. We further show that enforcing these axioms on learning individual value functions recovers the Shapley value for Dec-POMDPs, providing a principled bridge between reinforcement learning and classical cooperative game theory. Building on this framework, we introduce Shapley Machines and Banzhaf Machines, two generic algorithmic templates that can be instantiated with standard reinforcement learning methods. When applied to strong base algorithms such as IPPO and POAM, our methods consistently improve learning efficiency and generalisation to unseen agent types and conventions across NAHT benchmark tasks. The code of experiments is published on https://github.com/hsvgbkhgbv/axiomatic-rl-naht.
Sources
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning