Zachary Roch

2 accepted papers

2026

Distributionally Robust Markov Games with Average Reward

ICML 2026poster

We propose and study distributionally robust Markov games (DR‑MGs) with the average‑reward criterion as a crucial framework for multi-agent decision-making under model mismatches and over extended horizons. Under a standard irreducible assumption, we first derive a correspondence between the optimal…

Cited by 0 Source ↗Scholar ↗

2026

Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

Zachary Roch, George Atia, Yue Wang

ICML 2026poster

Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment may differ from its training dynamics. However, most existing studies focus on model-based settings and provide only asymptotic guarantees, hindering th…

Cited by 0 Source ↗Scholar ↗