LightNews
vthoma.bsky.social
Vinzenz Thoma
@vthoma.bsky.social
36 followers 48 following 3 posts
Student Researcher @ Google DeepMind PhD in RL & Game Theory @ ETH AI Center
Posts Media Videos Starter Packs
vthoma.bsky.social
Vinzenz Thoma @vthoma.bsky.social · Apr 22
[2/2] Interested? Talk with Jiawei at ICLR or check out the full version here: arxiv.org/abs/2407.10207. The paper is joint work Zebang Shen, Heinrich Nax, and Niao He.
Learning to Steer Markovian Agents under Model Uncertainty
Designing incentives for an adapting population is a ubiquitous problem in a wide array of economic applications and beyond. In this work, we study how to design additional rewards to steer multi-agen...
arxiv.org
vthoma.bsky.social
Vinzenz Thoma @vthoma.bsky.social · Apr 22
[1/2]Our work “Learning to steer Markovian Agents under Model Uncertainty” explores the problem of steering (unknown) learning dynamics in Markov Games towards desirable outcomes (e.g. Pareto optimal Nash).
My co-author Jiawei Huang is presenting it at ICLR on Apr 24, 3:00-5:30pm GMT+8, Poster #401.
2 2 3
Reposted by Vinzenz Thoma
robinchauhan.bsky.social
Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · Mar 10
E65: NeurIPS 2024 – Posters and Hallways 3

- Claire Bizon Monroc of Inria : WFCRL for Wind Farm Control
Andrew Wagenmaker of @ucberkeleyofficial.bsky.social : Leveraging Simulation to Bridge Sim-to-Real Gap
- @harwiltz.bsky.social of @mila-quebec.bsky.social : Multivariate Distributional RL
(cont)
1 2 2
vthoma.bsky.social
Vinzenz Thoma @vthoma.bsky.social · Feb 26
I'm at AAAI this week, presenting our paper “Computing Perfect Bayesian Equilibria in Sequential Auctions” (arxiv.org/abs/2312.04516) done at @eth-ai-center.bsky.social.

If interested, join the poster session (#657 on Saturday 12:30 – 14:30) or oral presentation (room 115C on Sunday 2pm).
Computing Perfect Bayesian Equilibria in Sequential Auctions with Verification
We present an algorithm for computing pure-strategy epsilon-perfect Bayesian equilibria in sequential auctions with continuous action and value spaces. Importantly, our algorithm includes a verificati...
arxiv.org
1 7