Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity

Qiuhao Wang, Yuqi Zha, Chin Pang Ho, Marek Petrik
2/14/2026

No official code found. Best implementation: Charliez7/robust-AMDP (0 stars, last commit 2025-05-28).

Semantic Scholar

Code Implementations(1)

Charliez7/robust-AMDPCommunity64%

This project is for ICML 2025 accepted paper "Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity"

00PythonMay 20, 20251 years ago

Similar Papers

Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning

100% match2026

Successor Features for Efficient Multi-Subject Controlled Text Generation

100% match2026

Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning

100% match1 repo342026

Characteristics Matching Based Hash Codes Generation for Efficient Fine-Grained Image Retrieval

100% match2026

Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction

100% match2026

Learning Input Encodings for Kernel-Optimal Implicit Neural Representations

100% match1 repo12026

Cite this paper

@article{wang2026provable,
  title  = {Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity},
  author = {Qiuhao Wang and Yuqi Zha and Chin Pang Ho and Marek Petrik},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:52e70f14d853aec041b0ec3980b8267dceb918c4},
  journal = {ICML 2025 2025}
}

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/52e70f14d853aec041b0ec3980b8267dceb918c4.svg)](https://codeofpaper.com/paper/52e70f14d853aec041b0ec3980b8267dceb918c4)

Discussion