3 papers
cs.LG2026
Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments
Florent Delgrange
The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed t…
cs.LG2026
Deep SPI: Safe Policy Improvement via World Models
Florent Delgrange, Raphael Avalos, Willem Röpke
Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in…
cs.AI2025
Composing Reinforcement Learning Policies, with Formal Guarantees
Florent Delgrange, Guy Avni, Anna Lukina +5
We propose a novel framework to controller design in environments with a two-level structure: a known high-level graph ("map") in which each vertex is populated by a Markov decisio…