Our work on the reproducibility of meta-RL baselines (Bandits + MDPs) with MAML and Reptile is at the Reproducibility in ML workshop (C2) #ICML2018 together with Arian Hosseini & Simon Guiroy @MILAMontreal

Like policy gradients? In "Expected Policy Gradients for Reinforcement Learning", we study various quadrature schemes to decrease variance in gradient estimates. Final version is now published in JMLR (Journal of Machine Learning Research). See jmlr.org/papers/v21/18-….

Kullback-Leibler divergence is not the same as Leibler-Kullback divergence

I'm excited to present our work on active reward learning at #NeurIPS2021! We propose a general way to make queries that are informative about the optimal policy. Joint work with Matteo Turchetta, Sebastian Tschiatschek, Kamil Ciosek, and Andreas Krause: arxiv.org/abs/2102.12466 👇(1/6)

Interested in Imitation Learning? You can do it using a single call to a Reinforcement Learning oracle. See our #ICLR2022 paper “Imitation Learning by Reinforcement Learning” (openreview.net/pdf?id=1zwleyt…).

Want to do imitation learning in a simple and efficient way? We released code for the ICLR 2022 paper “Imitation Learning by Reinforcement Learning”. See github.com/spotify-resear….

Interested in working on exciting ML ideas for Spotify? Join us! We are looking for a Research Scientist Intern to join our research lab in London for summer 2023. lifeatspotify.com/jobs/summer-in… Spotify Research

For anyone worried their LLM might be making stuff up, we made a budget‐friendly truth serum (semantic entropy + Bayesian). See for yourself: youtube.com/watch?v=x_8ORG… Paper: arxiv.org/pdf/2504.03579

Our new paper: using Fourier analysis to derive policy gradients: we recast the integrals as convolutions, which a Fourier transform turns into multiplications. The resulting analysis unifies existing policy gradient results. arxiv.org/abs/1802.06891

"Fourier Policy Gradients" by Matthew Fellows, Kamil Ciosek and Shimon Whiteson arxiv.org/pdf/1802.06891…

Learn about our work on "Expected Policy Gradients" in this 13min video by Kamil Ciosek - with Kamil Ciosek Shimon Whiteson youtube.com/watch?v=x2NFiP…