2021 – Machine Learning and Positioning Systems

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…

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

Ilona Bamiller: Benchmarking Offline Reinforcement Learning on an Autonomous Driving Application (LMU München, 2021)

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

Reinforcement Learning (RL) builds on the idea that an agent learns an optimal behavior through iterative interaction with an environment. In model-free reinforcement learning the agent does not have access…