Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation
cs.LG, cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Comments: 62 pages, 3 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic interactions among agents.
Terminology
Abstract
Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic interactions among agents. Distributionally robust Markov games (DRMGs) provide a principled framework for addressing such uncertainty, yet existing methods often rely on restrictive assumptions or scale poorly to large state and joint action spaces. We study online learning in general-sum DRMGs with general function approximation and ϕ-divergence uncertainty sets. We propose RoMEX- ϕ, a model-free framework that integrates equilibrium-based exploration with dual fitted learning. Through a functional dual representation of the robust multi-agent Bellman operator, RoMEX- ϕ enables tractable worst-case value estimation from nominal interaction data using a centered empirical robust discrepancy. We introduce the robust Multi-Agent Decoupling Coefficient (robust MADC) to characterize the intrinsic exploration complexity arising from strategic interactions and adversarial transition uncertainty. We establish sublinear robust regret guarantees governed by the robust MADC rather than explicitly by the state and joint action space sizes, replacing tabular dependence with intrinsic function-class complexity. Numerical experiments on a scalable general-sum DRMG under total variation uncertainty show that RoMEX- ϕ is substantially more resilient to transition shifts than its non-robust counterpart while remaining competitive with an exact tabular robust baseline. Our results provide a scalable framework for distributionally robust multi-agent reinforcement learning with general function approximation.
Sources
- Wasserstein Robust Reinforcement Learning
- Towards Minimax Optimality of Model-based Robust Reinforcement Learning
- Bilinear Classes: A Structural Framework for Provable Generalization in RL
- Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
- The Statistical Complexity of Interactive Decision Making
- Online Robust Reinforcement Learning with General Function Approximation
- Towards General Function Approximation in Zero-Sum Markov Games
- Minimax-Optimal Multi-Agent Robust Reinforcement Learning
- Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning
- Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation
- Representation Learning for General-sum Low-rank Markov Games
- Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data
- Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning
- EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
- Distributionally Robust Markov Games with Average Reward
- Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
- Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
- Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
- Robust Reinforcement Learning using Adversarial Populations
- Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks