Elizabeth Bates
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Elizabeth Bates has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Charles Constant
University College London, London, UK
1 shared publication - Chris Hicks
The Alan Turing Institute
1 shared publication - Marek Ziebart
University College London (UCL), London, United Kingdom
1 shared publication - Santosh Bhattarai
University College London
1 shared publication - Tobias Ritschel
University College London (UCL), London, United Kingdom
1 shared publication - Vasilios Mavroudis
The Alan Turing Institute
1 shared publication
Latest Publications
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-17
Photons × Force: Differentiable Radiation Pressure Modeling
We propose a system to optimize parametric designs subject to radiation pressure, i.e., the effect of light on the motion of objects. This is most relevant in the design of spacecraft, where radiation pressure presents the dominant non-conservative forcing mechanism, which is the case beyond approximately 800 km altitude. Despite its importance, the high computational cost of high-fidelity radiation pressure modeling has limited its use in large-scale spacecraft design, optimization, and space situational awareness applications. We enable this by offering three innovations in the simulation, in representation and in optimization: First, a practical computer graphics-inspired Monte-Carlo (MC) simulation of radiation pressure. The simulation is highly parallel, uses importance sampling and next-event estimation to reduce variance and allows simulating an entire family of designs instead of a single spacecraft as in previous work. Second, we introduce neural networks as a representation of forces from design parameters. This neural proxy model, learned from simulations, is inherently differentiable and can query forces orders of magnitude faster than a full MC simulation. Third, and finally, we demonstrate optimizing inverse radiation pressure designs, such as finding geometry, material or operation parameters that minimizes travel time, maximizes proximity given a desired end-point, minimize thruster fuel, trains mission control policies or allocated compute budget in extraterrestrial compute.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-17
Open AccessPhotons × Force: Differentiable Radiation Pressure Modeling
We propose a system to optimize parametric designs subject to radiation pressure, i.e., the effect of light on the motion of objects. This is most relevant in the design of spacecraft, where radiation pressure presents the dominant non-conservative forcing mechanism, which is the case beyond approximately 800 km altitude. Despite its importance, the high computational cost of high-fidelity radiation pressure modeling has limited its use in large-scale spacecraft design, optimization, and space situational awareness applications. We enable this by offering three innovations in the simulation, in representation and in optimization: First, a practical computer graphics-inspired Monte-Carlo (MC) simulation of radiation pressure. The simulation is highly parallel, uses importance sampling and next-event estimation to reduce variance and allows simulating an entire family of designs instead of a single spacecraft as in previous work. Second, we introduce neural networks as a representation of forces from design parameters. This neural proxy model, learned from simulations, is inherently differentiable and can query forces orders of magnitude faster than a full MC simulation. Third, and finally, we demonstrate optimizing inverse radiation pressure designs, such as finding geometry, material or operation parameters that minimizes travel time, maximizes proximity given a desired end-point, minimize thruster fuel, trains mission control policies or allocated compute budget in extraterrestrial compute.
- Open Access
- 26 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 221-232
Reward Shaping for Happier Autonomous Cyber Security Agents
As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense tasks. This work studies the impact of the reward signal that is provided to the agents when training for this task. Due to the nature of cybersecurity tasks, the reward signal is typically 1) in the form of penalties (e.g., when a compromise occurs), and 2) distributed sparsely across each defense episode. Such reward characteristics are atypical of classic reinforcement learning tasks where the agent is regularly rewarded for progress (cf. to getting occasionally penalized for failures). We investigate reward shaping techniques that could bridge this gap so as to enable agents to train more sample-efficiently and potentially converge to a better performance. We first show that deep reinforcement learning algorithms are sensitive to the magnitude of the penalties and their relative size. Then, we combine penalties with positive external rewards and study their effect compared to penalty-only training. Finally, we evaluate intrinsic curiosity as an internal positive reward mechanism and discuss why it might not be as advantageous for high-level network monitoring tasks.
- 26 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 221-232
Open AccessReward Shaping for Happier Autonomous Cyber Security Agents
As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense tasks. This work studies the impact of the reward signal that is provided to the agents when training for this task. Due to the nature of cybersecurity tasks, the reward signal is typically 1) in the form of penalties (e.g., when a compromise occurs), and 2) distributed sparsely across each defense episode. Such reward characteristics are atypical of classic reinforcement learning tasks where the agent is regularly rewarded for progress (cf. to getting occasionally penalized for failures). We investigate reward shaping techniques that could bridge this gap so as to enable agents to train more sample-efficiently and potentially converge to a better performance. We first show that deep reinforcement learning algorithms are sensitive to the magnitude of the penalties and their relative size. Then, we combine penalties with positive external rewards and study their effect compared to penalty-only training. Finally, we evaluate intrinsic curiosity as an internal positive reward mechanism and discuss why it might not be as advantageous for high-level network monitoring tasks.