Research archive
Questions worth making precise.
My work studies how agents learn, search, and remain reliable when information is hidden and other decision-makers can adapt.
R.01
Safe Observation Capacity for Opponent Exploitation under Showdown Censoring
A safe method for learning exploitable opponent behavior when folds censor private-card observations.
Imperfect-information games · Opponent exploitation · Safe active learning
R.02
CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules
Deterministic convergence guarantees and exploitability certificates for persistent partial public-chance evaluation.
Counterfactual regret · Public-chance sampling · Exploitability certificates
R.03
From Win Rate to Worst Case: Auditing Language-Model Policies in Imperfect-Information Games
Exact best-response audits reveal worst-case vulnerabilities that selected-opponent evaluations can miss.
Language models · Exploitability · Policy evaluation
R.04
Model-Guided Public-Belief Search
Research tools for scalable search in imperfect-information games.
Public-belief search · Imperfect information · Model-guided planning