Murray Shanahan

Classifying Options for Deep Reinforcement Learning

2016 · arXiv (Cornell University)

In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network …

Learning Diverse Representations for Fast Adaptation to Distribution Shift

2020 · arXiv (Cornell University)

The i.i.d. assumption is a useful idealization that underpins many successful approaches to supervised machine learning. However, its violation can lead to models that learn to exploit spurious correlations in the training data, rendering them …

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

2022 · arXiv (Cornell University)

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive …