regret bounds

2 papers across 2 sessions

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes

#3207 · Jasmine Bayrooti, Sattar Vakili, Amanda Prorok, Carl Henrik Ek

We derive no-regret guarantees for Thompson sampling in episodic reinforcement learning with Gaussian process modelling.

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Beyond

\tilde{O} (T http://www.w3.org/2000/svg

" width="400em" height="1.08em" viewBox="0 0 400000 1080" preserveAspectRatio="xMinYMin slice">) Constraint Violation for Online Convex Optimization with Adversarial Constraints

#914 · Abhishek Sinha, Rahul Vaze

This paper presents a tunable algorithm for online convex optimization with adversarial constraints that significantly reduces cumulative constraint violation below $O(\sqrt{T})$ by trading it off with regret.