Search Results for author:
Found 9 papers, 5 papers with code
GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations
However, research focusing on counterfactual explanations, specifically for RL agents with visual input, is scarce and does not go beyond identifying defective agents.
Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents
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.
Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systems
We evaluate our approach in an extensive user study, revealing that it is able to significantly contribute to the participants' understanding of an AI.
Dynamic Difficulty Adjustment in Virtual Reality Exergames through Experience-driven Procedural Content Generation
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.
Do Deep Neural Networks Forget Facial Action Units? -- Exploring the Effects of Transfer Learning in Health Related Facial Expression Recognition
We then fine-tune successively larger parts of this network to learn suitable representations for the task of automatic pain recognition.
Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents
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.
GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information.
Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps
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.
Are Bitcoin Bubbles Predictable? Combining a Generalized Metcalfe's Law and the LPPLS Model
We develop a strong diagnostic for bubbles and crashes in bitcoin, by analyzing the coincidence (and its absence) of fundamental and technical indicators.
