1

Generative Adversarial Networks for Global Illumination and Indirect Lighting as a Replacement for Ray-tracing in Older GPU Hardware
We give an overview of the different rendering methods and we demonstrate that the use of a Generative Adversarial Networks (GAN) for …
PDF Cite
Deep Reinforcement Learning for Robotic Hand Manipulation
Researchers have made a lot of progress in combining the advances in Deep Learning and the generalization and applicability of …
PDF Cite
Model Predictive-Actor Critic Reinforcement Learning for Dexterous Manipulation
Dexterous multi-fingered robotic hands represent a promising solution for robotic manipulators to perform a wide range of complex …
PDF Cite
A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education
Understanding which student support strategies mitigate dropout and improve student retention is an important part of modern higher …
PDF Cite
Knowledge Transfer using Model-Based Deep Reinforcement Learning
Deep reinforcement learning has recently been adopted for robot behavior learning, where robot skills are acquired and adapted from …
PDF Cite
A Boolean Task Algebra for Reinforcement Learning
The ability to compose learned skills to solve new tasks is an important property for lifelong-learning agents. In this work we …
PDF Cite Project
Utilising Uncertainty for Efficient Learning of Likely-Admissible Heuristics
Likely-admissible heuristics have previously been introduced as heuristics that are admissible with some probability. While such …
PDF Cite Supplementary Material
Discovery of Influence between Processes Represented by Hidden Markov Models
Learning the underlying structure between processes is a common problem found in the sciences, however not much work is dedicated …
PDF Cite
Learning Portable Representations for High-Level Planning
We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous …
PDF Cite Project
Combining Primitive DQNs for Improved Reinforcement Learning in Minecraft
We ask whether a reinforcement learning agent learns better by first learning the skills to perform smaller tasks in a complex …
PDF Cite