mugga – Page 2 – Machine Learning and Positioning Systems

Alexander Mattick: Beam Tracking as a Time-Varying Reinforcement Learning Problem

By mugga November 1, 20222023, 5G & 6G, Finished, Reinforcement Learning, Student Project

The envisioned transition to 5G and 6G technologies have started to transform the properties of established communication networks. In the core of this transformation lies the capability of Base Stations…

Abhinav Singh: Safe Imitation Learning for Beam Tracking

By mugga November 1, 20222022, 5G & 6G, Finished, Reinforcement Learning, Student Project

Lukas Frieß: Model-based Reinforcement Learning with First-Principle Models (FAU Erlangen-Nürnberg, 2021)

By mugga May 2, 20222021, Finished, Master Thesis, Reinforcement Learning

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)

By mugga May 2, 20222022, Finished, Master Thesis, Reinforcement Learning

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…

Lars Ulrich: Analyzing the Effect of Design Choices in Model-based Reinforcement Learning (FAU Erlangen-Nürnberg, 2022)

By mugga May 2, 20222022, Finished, Master Thesis, Reinforcement Learning

Hyeyoung Park: Interpretable Decision Tree Extraction using Imitation Learning and Locally Adaptive Optimization (LMU München, 2022)

By mugga May 2, 20222022, Finished, Master Thesis, Reinforcement Learning

Hyeyoung Park: Towards Interpretable (and Robust) Reinforcement Learning Policies through Local Lipschitzness and Randomization

By mugga May 2, 20222021, Finished, Reinforcement Learning, Student Project

Reinforcement Learning is broadly applicable for diverse tasks across many domains. On many problems, it has achieved superhuman performance [5]. However, the black-box neural networks used by modern RL algorithms…

Sebastian Fischer: Back to the Basics: Offline Reinforcement Learning with Least-Squares Methods for Policy Iteration (LMU München, 2021)

By mugga May 2, 20222021, Finished, Master Thesis, Reinforcement Learning

Recently, offline (sometimes also called ‘batch’) Reinforcement Learning (RL) algorithms have gained significant research traction [1]. The reason behind this is that – unlike in the classical Reinforcement Learning formulation…

Matthias Gruber: Learning to Avoid your Supervisor (LMU München, 2021)

By mugga May 2, 20222021, Finished, Master Thesis, Reinforcement Learning

Daniel Landgraf: Hierarchical Learning and Model Predictive Control (FAU Erlangen-Nürnberg, 2020)

By mugga May 2, 20222020, Finished, Master Thesis, Reinforcement Learning

Recent progress in (deep) learning algorithms has shown great potential to learn complex tasks purely from large numbers of samples or interactions with the environment. However, performing such interactions can…