7 papers
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…
Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
Dillon Z. Chen, Johannes Zenn, Tristan Cinquin +1
We study the usage of language models (LMs) for planning over world models specified in the Planning Domain Definition Language (PDDL). We prompt LMs to generate Python programs th…
Better Training Data Attribution via Better Inverse Hessian-Vector Products
Andrew Wang, Elisa Nguyen, Runshi Yang +3
Training data attribution (TDA) provides insights into which training data is responsible for a learned model behavior. Gradient-based TDA methods such as influence functions and u…