Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Steven's Homepage
About me
Page not in menu
This is a page not in th emain menu
Posts
portfolio
Master’s Thesis Research
Published:
The spinning projectile extreme environment robot
Autonomous Navigation at Toshiba Research
Published:
Generalized embodied navigation models, trained on ground robots that seamlessly transfer to aerial robots
publications
Improving Visual Feature Extraction in Glacial Environments
Published in IEEE Robotics and Automation Letters, 2019
Embodied Visual Navigation With Automatic Curriculum Learning in Real Environments
Published in IEEE Robotics and Automation Letters, 2022
Modeling Partially Observable Systems using Graph-Based Memory and Topological Priors
Published in The 4th Annual Learning for Dynamics and Control Conference, 2022
A framework for real-world multi-robot systems running decentralized GNN-based policies
Published in 2022 International Conference on Robotics and Automation (ICRA), 2022
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning
Published in Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023
POPGym: Benchmarking Partially Observable Reinforcement Learning
Published in The Eleventh International Conference on Learning Representations, 2023
Generalised f-Mean Aggregation for Graph Neural Networks
Published in Thirty-seventh Conference on Neural Information Processing Systems, 2023
Reinforcement Learning with Fast and Forgetful Memory
Published in Thirty-seventh Conference on Neural Information Processing Systems, 2023
Recurrent Reinforcement Learning with Memoroids
Published in Thirty-eighth Conference on Neural Information Processing Systems, 2024
talks
An Introduction to Reinforcement Learning
Published:
An hour-long talk deriving the basics of value-based and policy-based reinforcement learning.
Reinforcement Learning under Partial Observability
Published:
Reinforcement learning agents have mastered complex games like Go, Atari, or DotA 2, outperforming the best humans on Earth. Yet, these impressive feats are constrained to games or simulations. What prevents us from training superintelligent robots using reinforcement learning? In this talk, we will explore one major roadblock: limited and imperfect sensor data. We will investigate deep memory models as a solution to this challenge. Our journey will cover a number of deep learning architectures, such as recurrent neural networks, graph neural networks, and linear transformers.
Introduction to Reinforcement Learning
Published:
A 1.5 hour tutorial on RL, given for the ELLIS 2024 Probabilistic Machine Learning Summer School.
teaching
Teaching Assistant: Mobile Robot Systems
University course, University of Cambridge, Department of Computer Science and Technology, 2021
Teaching students the first bits of robotics, with final projects utilizing ROS and turtlebots.
Teaching Assistant: Introduction to Robotics
University course, University of Cambridge, Department of Computer Science and Technology, 2022
Teaching students the first bits of robotics, with final projects utilizing ROS and turtlebots.
Adjunct Lecturer: Deep Reinforcement Learning
University course, University of Cambridge, Department of Computer Science and Technology, 2024
This is part of the R255 series for Part III and MPhil students. Slides are available here:
Lecturer: Introduction to Deep Learning
University course, University of Macau, Department of Computer and Information Science, 2024
A master’s level course on deep learning.