activity
20182025
most citedVariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning

65 citations · 67 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG20252 cited

A Safety and Security Framework for Real-World Agentic Systems

Shaona Ghosh, Barnaby Simkin, Kyriacos Shiarlis +9

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attribut…

cs.LG2025

Gandalf the Red: Adaptive Security for LLMs

Niklas Pfister, Václav Volhejn, Manuel Knott +23

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior an…

cs.LG2023

Hierarchical Imitation Learning for Stochastic Environments

Maximilian Igl, Punit Shah, Paul Mougin +5

Many applications of imitation learning require the agent to generate the full distribution of behaviour observed in the training data. For example, to evaluate the safety of auton…

cs.LG2022

Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation

Maximilian Igl, Daewoo Kim, Alex Kuefler +7

Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such car…

cs.LG201965 cited

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning

Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl +4

Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions…

cs.LG2018

Learning from Demonstration in the Wild

Feryal Behbahani, Kyriacos Shiarlis, Xi Chen +8

Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically…