← Search

Yantian Wang

2 accepted papers

2026

InfraRL: A Benchmark for Constrained Resource Allocation in Large-Scale Infrastructure Asset Management

ICML 2026poster

Optimizing maintenance strategies for large-scale infrastructure is a critical sequential decision-making problem, exemplified by the high-stakes domain of bridge management. While Reinforcement Learning (RL) offers a theoretical framework for such problems, practical deployment necessitates offline…

Cited by 0SourceScholar
2026

Negotiated Reasoning: On Provably Addressing Relative Over-Generalization

ICLR 2026poster

We focus on the relative over-generalization (RO) issue in fully cooperative multi-agent reinforcement learning (MARL). Existing methods show that endowing agents with reasoning can help mitigate RO empirically, but there is little theoretical insight. We first prove that RO is avoided when agents s…

Cited by 0SourceScholar