paper-with-me

홈 › Papers

POWQMIX: Weighted Value Factorization with Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning

2024-05-13 · Chang Huang, Shatong Zhu, Junqiao Zhao, Hongtu Zhou, Chen Ye, Tiantian Feng, Changjun Jiang

Value function factorization methods are commonly used in cooperative multi-agent reinforcement learning, with QMIX receiving significant attention. Many QMIX-based methods introduce monotonicity constraints between the joint action value and individual action values to achieve decentralized execution. However, such constraints limit the representation capacity of value factorization, restricting the joint action values it can represent and hindering the learning of the optimal policy. To address this challenge, we propose the Potentially Optimal Joint Actions Weighted QMIX (POWQMIX) algorithm, which recognizes the potentially optimal joint actions and assigns higher weights to the corresponding losses of these joint actions during training. We theoretically prove that with such a weighted training approach the optimal policy is guaranteed to be recovered. Experiments in matrix games, difficulty-enhanced predator-prey, and StarCraft II Multi-Agent Challenge environments demonstrate that our algorithm outperforms the state-of-the-art value-based multi-agent reinforcement learning methods.

📄 PDF Abstract BibTeX arXiv:2405.08036

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningStarcraftStarcraft II

Similar Papers 제목 키워드 기반

Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss

2013-03-07 · Ben London, Theodoros Rekatsinas, Bert Huang, Lise Getoor

We propose a modular framework for multi-relational learning via tensor decomposition. In our learning setting, the training data contains multiple types of relationships among a set of objects, which we represent by a s…

Relational ReasoningTensor Decomposition

Self-Similar Epochs: Value in Arrangement

2018-03-14 · ICLR 2019 5 · Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias

Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that sub-epochs comprise of independent random samples of the t…

Model approximation in MDPs with unbounded per-step cost

2024-02-13 · Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang

We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process $\mathcal{M}$ when we only have access to an approximate model $\hat{\mathcal{M}}$. How well does an o…

An Iterative Algorithm for Regularized Non-negative Matrix Factorizations

2024-10-30 · Steven E. Pav

We generalize the non-negative matrix factorization algorithm of Lee and Seung to accept a weighted norm, and to support ridge and Lasso regularization. We recast the Lee and Seung multiplicative update as an additive up…

ReMIX: Regret Minimization for Monotonic Value Function Factorization in Multiagent Reinforcement Learning

2023-02-11 · Yongsheng Mei, Hanhan Zhou, Tian Lan

Value function factorization methods have become a dominant approach for cooperative multiagent reinforcement learning under a centralized training and decentralized execution paradigm. By factorizing the optimal joint a…

Decision Makingreinforcement-learningReinforcement Learning (RL)Starcraft