Alexander Kuhnle

A Proposition-based Abstractive Summarizer

2016 · Apollo (University of Cambridge)

Abstractive summarisation is not yet common amongst today's deployed and research systems. Most existing systems either extract sentences or compress individual sentences. In this paper, we present a summariser that works by a different paradigm. …

Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents

2021 · arXiv (Cornell University)

In this article we study the problem of training intelligent agents using Reinforcement Learning for the purpose of game development. Unlike systems built to replace human players and to achieve super-human performance, our agents aim …