activity
20202026
most citedA Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes

7 citations · 36 across the 21 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.LG2026

Policy Iteration Is Not Strongly Polynomial for Deterministic Markov Decision Processes: The Price of Algorithmic Anarchy

Han Zhong, Yinyu Ye

We establish exponential iteration lower bounds in the number of states for Howard's policy iteration on deterministic discounted and average-reward Markov decision processes (MDPs…

stat.ML2026

Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits

Kaifei Wang, Yinyu Ye, Han Zhong

Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off between worst-ca…