Conservative Offline Policy Adaptation in Multi-Agent Games

Chengjie Wu, Pingzhong Tang, Jun Yang, Yujing Hu, Tangjie Lv +2 more
2/12/2026

No official code found. Best implementation: zbzhu99/madiff (113 stars, MIT, last commit 2025-06-26).

DOISemantic Scholar

Code Implementations(1)

zbzhu99/madiffCommunity100%
MIT

Implementation of "MADiff: Offline Multi-agent Learning with Diffusion Models"

11319Shell, PythonOct 13, 20231 years agoMIT

Similar Papers

Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification

98% match2026

Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach

98% match1 repo162026

Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice

97% match2026

Grounding Multimodal Large Language Model in GUI World

95% match2026

Learning Rate Free Bayesian Inference in Constrained Domains

95% match2026

Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling

95% match1 repo2026

Cite this paper

@article{wu2026conservative,
  title  = {Conservative Offline Policy Adaptation in Multi-Agent Games},
  author = {Chengjie Wu and Pingzhong Tang and Jun Yang and Yujing Hu and Tangjie Lv and Changjie Fan and Chongjie Zhang},
  year   = {2026},
  doi    = {10.52202/075280-2260},
  url    = {https://doi.org/10.52202/075280-2260},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/5c104465c3d2c5897f4ae1338c90551e233e27cf.svg)](https://codeofpaper.com/paper/5c104465c3d2c5897f4ae1338c90551e233e27cf)

Discussion