91 citations · 213 across the 16 of their papers we have counts for
18 papers
Evaluating LLMs as Interpretable Controllers for Dynamical Systems
Aleksander Østensen, Alberto Mino Calero, Anastasios M. Lekkas +1
Large Language Models (LLMs) are increasingly used for decision-making and reasoning tasks, yet their potential as controllers for physical systems remains largely unexplored. This…
Realistic Counterfactual Explanations for Machine Learning-Controlled Mobile Robots using 2D LiDAR
Sindre Benjamin Remman, Anastasios M. Lekkas
This paper presents a novel method for generating realistic counterfactual explanations (CFEs) in machine learning (ML)-based control for mobile robots using 2D LiDAR. ML models, e…
Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective
Sindre Benjamin Remman, Bjørn Andreas Kristiansen, Anastasios M. Lekkas
In this work, we use optimal control to change the behavior of a deep reinforcement learning policy by optimizing directly in the policy's latent space. We hypothesize that distinc…
Discovering Behavioral Modes in Deep Reinforcement Learning Policies Using Trajectory Clustering in Latent Space
Sindre Benjamin Remman, Anastasios M. Lekkas
Understanding the behavior of deep reinforcement learning (DRL) agents is crucial for improving their performance and reliability. However, the complexity of their policies often m…
Real-Time Counterfactual Explanations For Robotic Systems With Multiple Continuous Outputs
Vilde B. Gjærum, Inga Strümke, Anastasios M. Lekkas +1
Although many machine learning methods, especially from the field of deep learning, have been instrumental in addressing challenges within robotic applications, we cannot take full…
Approximating a deep reinforcement learning docking agent using linear model trees
Vilde B. Gjærum, Ella-Lovise H. Rørvik, Anastasios M. Lekkas
Deep reinforcement learning has led to numerous notable results in robotics. However, deep neural networks (DNNs) are unintuitive, which makes it difficult to understand their pred…