Christopher G. Lucas — accepted AI-conference papers

2025

Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

Ruaridh Mon-Williams, Max Taylor-Davies, Elizabeth Mieczkowski, Natalia Vélez, Neil R Bramley, Yanwei Wang +2

NeurIPS 2025poster

Humans are remarkably adept at collaboration, able to infer the strengths and weaknesses of new partners in order to work successfully towards shared goals. To build AI systems with this capability, we must first understand its building blocks: does such flexibility require explicit, dedicated mecha…

Cited by 0 Source ↗Scholar ↗

2025

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

Samuel Garcin, Trevor McInroe, Pablo Samuel Castro, Christopher G. Lucas, David Abel, Prakash Panangaden +1

ICLR 2025poster

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether the same information will be relevant to both the actor and t…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Bayesian Program Learning by Decompiling Amortized Knowledge

Alessandro B. Palmarini, Christopher G. Lucas, Siddharth N

ICML 2024poster

DreamCoder is an inductive program synthesis system that, whilst solving problems, learns to simplify search in an iterative wake-sleep procedure. The cost of search is amortized by training a neural search policy, reducing search breadth and effectively "compiling" useful information to compose pro…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design

Samuel Garcin, James Doran, Shangmin Guo, Christopher G. Lucas, Stefano V Albrecht

ICML 2024poster

Autonomous agents trained using deep reinforcement learning (RL) often lack the ability to successfully generalise to new environments, even when these environments share characteristics with the ones they have encountered during training. In this work, we investigate how the sampling of individual…

Cited by 11 Source ↗PDF ↗Scholar ↗

2023

Non-Compositionality in Sentiment: New Data and Analyses

Verna Dankers, Christopher G. Lucas

EMNLP 2023short findings

When natural language phrases are combined, their meaning is often more than the sum of their parts. In the context of NLP tasks such as sentiment analysis, where the meaning of a phrase is its sentiment, that still applies. Many NLP studies on sentiment analysis, however, focus on the fact that sen…

Cited by 0 Source ↗code ↗Scholar ↗