paper-with-me

홈 › Papers

Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning

2025-11-12 · Tianmeng Hu, Yongzheng Cui, Rui Tang, Biao Luo, Ke Li arxiv

Value decomposition is a central approach in multi-agent reinforcement learning (MARL), enabling centralized training with decentralized execution by factorizing the global value function into local values. To ensure individual-global-max (IGM) consistency, existing methods either enforce monotonicity constraints, which limit expressive power, or adopt softer surrogates at the cost of algorithmic complexity. In this work, we present a dynamical systems analysis of non-monotonic value decomposition, modeling learning dynamics as continuous-time gradient flow. We prove that, under approximately greedy exploration, all zero-loss equilibria violating IGM consistency are unstable saddle points, while only IGM-consistent solutions are stable attractors of the learning dynamics. Extensive experiments on both synthetic matrix games and challenging MARL benchmarks demonstrate that unconstrained, non-monotonic factorization reliably recovers IGM-optimal solutions and consistently outperforms monotonic baselines. Additionally, we investigate the influence of temporal-difference targets and exploration strategies, providing actionable insights for the design of future value-based MARL algorithms.

📄 PDF Abstract BibTeX arXiv:2511.09792

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Revisiting the Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning

2021-09-29 · Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu 외

QMIX, a popular MARL algorithm based on the monotonicity constraint, has been used as a baseline for the benchmark environments, such as Starcraft Multi-Agent Challenge (SMAC), Predator-Prey (PP). Recent variants of QMI…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+3

State-Dependent Lyapunov Analysis of Rank-1 Matrix Factorization

2026-04-28 · Jaehong Moon arxiv

We study gradient descent for rank-1 matrix factorization through a state-dependent Lyapunov perspective. The central object is a parameterized quadratic certificate $I(δ;\,\cdot)$ whose boundary-inward property induces …

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models

2023-02-08 · Mohammadreza Banaei, Klaudia Bałazy, Artur Kasymov, Rémi Lebret 외

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitio…

On the Identifying Power of Monotonicity for Average Treatment Effects

2024-05-23 · Yuehao Bai, Shunzhuang Huang, Sarah Moon, Azeem M. Shaikh 외

In the context of a binary outcome, treatment, and instrument, Balke and Pearl (1993, 1997) establish that the monotonicity condition of Imbens and Angrist (1994) has no identifying power beyond instrument exogeneity for…

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

2019-05-14 · Kyunghwan Son, Daewoo Kim, Wan Ju Kang, David Earl Hostallero 외

We explore value-based solutions for multi-agent reinforcement learning (MARL) tasks in the centralized training with decentralized execution (CTDE) regime popularized recently. However, VDN and QMIX are representative e…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1