7 papers
Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning
Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen +1
We tackle the challenge of building embodied AI agents that can reliably solve long-horizon planning problems. Imitation learning from demonstrations has shown itself to be effecti…
Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems
Parand A. Alamdari, Toryn Q. Klassen, Sheila A. McIlraith
We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing…
Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
Chandler Smith, Marwa Abdulhai, Manfred Diaz +83
Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with bo…
Satisficing and Optimal Generalised Planning via Goal Regression (Extended Version)
Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen +1
Generalised planning (GP) refers to the task of synthesising programs that solve families of related planning problems. We introduce a novel, yet simple method for GP: given a set…
Pushdown Reward Machines for Reinforcement Learning
Giovanni Varricchione, Toryn Q. Klassen, Natasha Alechina +3
Reward machines (RMs) are automata structures that encode (non-Markovian) reward functions for reinforcement learning (RL). RMs can reward any behaviour representable in regular la…
Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data
Andrew C. Li, Toryn Q. Klassen, Andrew Wang +2
Grounding language in perception and action is a key challenge when building situated agents that can interact with humans, or other agents, via language. In the past, addressing t…