1 code implementation • 24 Feb 2023 • Tobias Huber, Maximilian Demmler, Silvan Mertes, Matthew L. Olson, Elisabeth André
However, research focusing on counterfactual explanations, specifically for RL agents with visual input, is scarce and does not go beyond identifying defective agents.
no code implementations • 21 Oct 2022 • Yael Septon, Tobias Huber, Elisabeth André, Ofra Amir
Methods that help users understand the behavior of such agents can roughly be divided into local explanations that analyze specific decisions of the agents and global explanations that convey the general strategy of the agents.
no code implementations • 19 Jul 2022 • Silvan Mertes, Christina Karle, Tobias Huber, Katharina Weitz, Ruben Schlagowski, Elisabeth André
We evaluate our approach in an extensive user study, revealing that it is able to significantly contribute to the participants' understanding of an AI.
no code implementations • 19 Aug 2021 • Tobias Huber, Silvan Mertes, Stanislava Rangelova, Simon Flutura, Elisabeth André
As a proof-of-concept, we implement an initial prototype in which the player must traverse a maze that includes several exercise rooms, whereby the generation of the maze is realized by a neural network.
no code implementations • 15 Apr 2021 • Pooja Prajod, Dominik Schiller, Tobias Huber, Elisabeth André
We then fine-tune successively larger parts of this network to learn suitable representations for the task of automatic pain recognition.
1 code implementation • 18 Jan 2021 • Tobias Huber, Benedikt Limmer, Elisabeth André
One of the most prominent methods for explaining the behavior of Deep Reinforcement Learning (DRL) agents is the generation of saliency maps that show how much each pixel attributed to the agents' decision.
1 code implementation • 22 Dec 2020 • Silvan Mertes, Tobias Huber, Katharina Weitz, Alexander Heimerl, Elisabeth André
By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information.
1 code implementation • 18 May 2020 • Tobias Huber, Katharina Weitz, Elisabeth André, Ofra Amir
Specifically, we augment strategy summaries that extract important trajectories of states from simulations of the agent with saliency maps which show what information the agent attends to.
1 code implementation • 15 Mar 2018 • Spencer Wheatley, Didier Sornette, Tobias Huber, Max Reppen, Robert N. Gantner
We develop a strong diagnostic for bubbles and crashes in bitcoin, by analyzing the coincidence (and its absence) of fundamental and technical indicators.