3 papers
cs.LG2025
On the optimization dynamics of RLVR: Gradient gap and step size thresholds
Joe Suk, Yaqi Duan
Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a pr…
stat.ML2024
Adaptive Smooth Non-Stationary Bandits
Joe Suk
We study a -armed non-stationary bandit model where rewards change smoothly, as captured by Hölder class assumptions on rewards as functions of time. Such smooth changes are par…
cs.LG2024
Non-Stationary Dueling Bandits Under a Weighted Borda Criterion
Joe Suk, Arpit Agarwal
In -armed dueling bandits, the learner receives preference feedback between arms, and the regret of an arm is defined in terms of its suboptimality to a arm. T…