Thomas Rupf

Huge thanks to my co-authors @mar_baga, @vlastelicap, @arkrause! Paper: arxiv.org/abs/2510.20264 (5/5)

OpTI-BFM bares similarities with LinUCB for Bandits which we use to prove sublinear regret in episodic settings under mild assumptions. Because it's online, OpTI-BFM can also adapt to time-varying (non-stationary) rewards by decaying the weight on older observations. (4/5)

Excited to share that our paper "Optimistic Task Inference for Behavior Foundation Models" was accepted for ICLR 2026. BFMs are great at zero-shot RL, but task inference requires a dataset with reward labels. Our method OpTI-BFM offers an online alternative. (1/5)

Last week I presented our last work: 🐝“Epistemically-guided forward backward exploration (FBEE)”🐝 at the @RL_Conference TLDR: Active learning for unsupervised RL

When multiple tasks need improvements, fine-tuning a generalist policy becomes tricky. How do we allocate a demonstration budget across a set of tasks of varied difficulty and familiarity? We are presenting a possible solution at ICML on Wednesday! (1/3)

If this sounds interesting, come by on Tuesday, 4:30 pm – 7:00 pm, West Exhibition Hall B2–B3 #W-618. Collaborators: @mar_baga, @nicoguertler, @JonasFrey96, @GMartius arxiv.org/abs/2410.08751… (3/3)

Our method tackles the occupancy matching objective directly at test-time by estimating the agent's occupancy with samples from a learned world model and matching it to the expert occupancy using Optimal Transport. (2/3)

Zero-shot imitation from just a single sparse demonstration is hard. Goal-conditioned methods tend to “greedily" move from one state to the next and lose the big picture. We're presenting an alternative approach on Tuesday at #ICML2025. (1/3)