Physics Aligned Diffusion Models for Wireless Channels
Physics-aligned diffusion models can be used to generate realistic
wireless channel data while preserving relevant physical properties.
Haris Asif: Quantum Circuit Optimization via Hierarchical Reinforcement Learning (FAU Erlangen-Nürnberg, 2024)
Motivation / Related Work Optimizing quantum circuits is essential for various applications, such as chemical simulations, due to the inherent complexity of quantum systems and the current limitations of quantum…
Thorsten Bescher: Schedule-Net and Gumbel-Alpha-Zero Play-to-Plan: a Hybrid Approach for the Job-Shop Scheduling Problem (FAU Erlangen-Nürnberg, 2024)
Motivation / Related Work Recently, reinforcement learning (RL) is applied frequently for combinatorial optimization problems [1] with real world applications, e.g., the job-shop scheduling problem (JSSP) or the travelling salesman…
Stephan Geisler: Designing and training foundation models for positioning applications (FAU Erlangen-Nürnberg, 2024)
Foundation models (like OpenAI’s GPT-4/ChatGPT [1] or Meta’s Llama 2 [2]) have been a disruptive technology that within just few months has started to transform the modus operandi of several industries. There have…
Nicolas Kolbenschlag: Automated Generation of Block-Encodings for Quantum Policy Iteration (FAU Erlangen-Nürnberg, 2024)
Motivation The rise of quantum computing has offered new opportunities to achieve computational tasks that classical computers cannot. However, to achieve quantum advantage over classical algorithms, it is necessary to…
Alexander Mattick: Reinforcement Learning for Node Selection in Branch-and-Bound (FAU Erlangen-Nürnberg, 2023)
1 Introduction The branch-and-bound algorithm is a fundamental solver for linear mixed integer programming problems. It is used to solve optimization problems with a combination of continuous and integer variables.…
Yongxu Ren: Variational Quantum Compiling with (Deep) Reinforcement Learning (FAU Erlangen-Nürnberg, 2023)
MotivationQuantum computing promises to revolutionize many areas that are hard or impossible to approach with tra- ditional computers. However, due to rigid hardware restrictions and noise sensitivity of currently available…
Lukas Frieß: Model-based Reinforcement Learning with First-Principle Models (FAU Erlangen-Nürnberg, 2021)
Motivation Reinforcement learning (RL) is increasingly used in robotics to learn complex tasks from repeated interactions with the environment. For example, a mobile robot can learn to avoid an obstacle…
Dinesh Parthasarathy: Safe Monte Carlo Tree Search using Learned Safety Critics (FAU Erlangen-Nürnberg, 2022)
Thesis available for download here: Dinesh Parthsarathy: Safe Monte Carlo Tree Search using Learned Safety Critics Background Reinforcement Learning and planning are two research fields that have shown great success…