Christoph Weinhuber
I am a second-year PhD student at the University of Oxford, where I study Artificial Intelligence with a focus on decision-making under uncertainty and long-term goal reasoning. I currently work at Intrinsic, an AI robotics group at Google. My research focuses on agentic AI, stochastic planning and reinforcement learning, often involving temporally extended goals expressed through logics. I am very fortunate to be supervised by Giuseppe De Giacomo, Dave Parker and Alessandro Abate.
Publications
- Formal Foundations of Agentic Business Process Management
- Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions
- Multi-Property Synthesis
- Good-for-MDP State Reduction for Stochastic LTL Planning
- A Requirements Engineering-Driven Methodology for Planning Domain Generation via LLMs with Invariant-Based Refinement
- Emerson-Lei and Manna-Pnueli Games for LTLf+ and PPLTL+ Synthesis
- Solving MDPs with LTLf+ and PPLTL+ Temporal Objectives
- Explaining Control Policies through Predicate Decision Diagrams
- Code Simulation as a Proxy for High-order Tasks in Large Language Models
- Code simulation challenges for large language models
- Federated learning with swift: An extension of flower and performance evaluation
- Language models as a service: Overview of a new paradigm and its challenges
- dtControl 2.0: explainable strategy representation via decision tree learning steered by experts