Reinforcement learning researcher at Hanoi UST focused on robust Monte-Carlo planning and convergence guarantees
5
papers here
5
reviewed by Evolve
3
first-author
2
corresponding
—
works · OpenAlex
2
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
This axis would measure cumulative research output — total works, venue spread, and productivity trajectory. The current OpenAlex snapshot lacks the aggregates needed to compute it, so no output score is available for this profile yet.
Impact—
This axis would measure citation impact — total citations, h-index trajectory, and community uptake. The record is too early-stage to score (h-index 2, i10-index 1, with most output dated 2026), so impact is left unscored rather than estimated.
Focus0/100
Scores a full 100/100 because the OpenAlex field distribution contains exactly one field — reinforcement learning — and all five indexed topics (robotics RL, AI in games, bandit algorithms, GAN-based image synthesis, adversarial robustness) stay within learning, planning, and decision-making.
Collaboration41/100
Scores 39/100 from the OpenAlex co-author network: six distinct coauthors in the last three years — Kishan Panaganti, Brahim Driss, Adam Wierman, Tung Tran, Viet Bao Mai, and Hoang Ta. The pool is compact, yet first- and last-author positions on both Evolve-reviewed papers indicate the researcher leads the projects this network produces.
Activity77/100
Scores 77/100 from OpenAlex yearly counts: 13 works in the last three years, with the output curve rising from 2 works in 2020 and 2 in 2022 to 9 works in 2026 — the most productive year on record, coinciding with both Evolve-reviewed arXiv papers.
Reproducibility48/100
Scores 55/100 (reproMean) from a single Evolve-assessed paper (reproPapers = 1). Both reviewed arXiv works carry a medium repro-readiness rating: proofs are described as sound but conditional, experiments are small-scale and, in the robust-MCTS paper, transition-only, with constants hidden and convergence claims tied to specific algorithmic assumptions.
Research summary
Tuan Dam is a reinforcement learning researcher at Hanoi University of Science and Technology (Vietnam) whose work centers on the algorithmic foundations of Monte-Carlo planning. The OpenAlex record shows an unusually focused profile: the field distribution maps entirely to reinforcement learning, and indexed topics are led by Reinforcement Learning in Robotics (12), Artificial Intelligence in Games (7), and Advanced Bandit Algorithms Research (5), with smaller clusters in GAN-based image synthesis and adversarial robustness. Activity is accelerating — 13 works in the last three years, including 9 in 2026, the strongest year recorded. Two 2026 arXiv papers reviewed by Evolve anchor this profile: Graph-Based Stochastic Power-UCT (last-authored), which adds power-mean backups and depth-keyed DAG merging to graph MCTS with a proven O(n^-1/2) root convergence rate, and Online Robust Reinforcement Learning Through Monte-Carlo Planning (first-authored), identified as the first robust MCTS matching the standard root rate. Citation metrics remain early-stage (h-index 2, i10-index 1), so impact is not yet scored. Collaboration is compact — six distinct coauthors in three years, including Kishan Panaganti, Brahim Driss, Adam Wierman, Tung Tran, Viet Bao Mai, and Hoang Ta — with the researcher in leading author positions on reviewed work.
Collaboration pattern
Collaboration is compact but consequential: OpenAlex counts six distinct coauthors over the last three years, and the frequent-coauthor list spans Kishan Panaganti, Brahim Driss, Adam Wierman, Tung Tran, Viet Bao Mai, and Hoang Ta — a mix of Vietnam-based and international partners. On the two Evolve-reviewed papers the researcher appears once as first author and once as last author, indicating leadership of the projects rather than peripheral participation; the collaboration dimension scores 39/100.
Research keywords
Highlights
Graph-based stochastic Power-UCT with proven O(n^-1/2) convergence
First robust MCTS matching the standard O(n^-1/2) root rate
A convergence-first agenda across two 2026 papers
Timeline
- 2020Earliest year in the OpenAlex record, with 2 indexed works.
- 20222 indexed works appear in the OpenAlex counts-by-year series.
- 2023A quieter year, with 1 indexed work in the OpenAlex record.
- 2024Output returns to 2 indexed works in the OpenAlex series.
- 20252 indexed works precede the 2026 acceleration.
- 2026Strongest year: 9 indexed works, including both Evolve-reviewed arXiv papers on graph-based stochastic Power-UCT and online robust RL through Monte-Carlo planning.
Papers in the Evolve catalog
Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation
- first author
Online Robust Reinforcement Learning Through Monte-Carlo Planning
- first authorcorresponding
Power Mean Estimation in Stochastic Continuous Monte Carlo Tree Search
- first authorcorresponding
Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- All bibliometric scores derive from OpenAlex records only; Scopus, Google Scholar, and other databases are not reflected.
- Output and impact dimensions are unscored: the snapshot's citation aggregates (h-index 2, i10-index 1) are too early-stage to support a reliable estimate.
- The reproducibility dimension rests on one Evolve-assessed paper out of two reviewed.
- Identity is name-resolved from public bibliographic data (OpenAlex, ORCID 0000-0001-7422-139X); Tuan Dam is a common Vietnamese name, so the affiliation match should be independently confirmed.