218 citations · 811 across the 15 of their papers we have counts for
19 papers
Comparative analysis of machine learning methods for active flow control
Fabio Pino, Lorenzo Schena, Jean Rabault +1
Machine learning frameworks such as Genetic Programming (GP) and Reinforcement Learning (RL) are gaining popularity in flow control. This work presents a comparative analysis of th…
A review on deep reinforcement learning for fluid mechanics: an update
Jonathan Viquerat, Philippe Meliga, Elie Hachem
In the past couple of years, the interest of the fluid mechanics community for deep reinforcement learning (DRL) techniques has increased at fast pace, leading to a growing bibliog…
Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
In this article we study the problem of training intelligent agents using Reinforcement Learning for the purpose of game development. Unlike systems built to replace human players…
Policy-based optimization: single-step policy gradient method seen as an evolution strategy
Jonathan Viquerat, Régis Duvigneau, Philippe Meliga +2
This research reports on the recent development of a black-box optimization method based on single-step deep reinforcement learning (DRL), and on its conceptual proximity to evolut…
Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Recent advances in Deep Reinforcement Learning (DRL) have largely focused on improving the performance of agents with the aim of replacing humans in known and well-defined environm…
Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Deep Reinforcement Learning achieves very good results in domains where reward functions can be manually engineered. At the same time, there is growing interest within the communit…
DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
In this paper we introduce DeepCrawl, a fully-playable Roguelike prototype for iOS and Android in which all agents are controlled by policy networks trained using Deep Reinforcemen…
Process Discovery for Structured Program Synthesis
Dell Zhang, Alexander Kuhnle, Julian Richardson +1
A core task in process mining is process discovery which aims to learn an accurate process model from event log data. In this paper, we propose to use (block-) structured programs…
Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning
Hongwei Tang, Jean Rabault, Alexander Kuhnle +2
This paper focuses on the active flow control of a computational fluid dynamics simulation over a range of Reynolds numbers using deep reinforcement learning (DRL). More precisely,…
Going Beneath the Surface: Evaluating Image Captioning for Grammaticality, Truthfulness and Diversity
Huiyuan Xie, Tom Sherborne, Alexander Kuhnle +1
Image captioning as a multimodal task has drawn much interest in recent years. However, evaluation for this task remains a challenging problem. Existing evaluation metrics focus on…
Direct shape optimization through deep reinforcement learning
Jonathan Viquerat, Jean Rabault, Alexander Kuhnle +3
Deep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements. Still, much remains to be explo…
What is needed for simple spatial language capabilities in VQA?
Alexander Kuhnle, Ann Copestake
Visual question answering (VQA) comprises a variety of language capabilities. The diagnostic benchmark dataset CLEVR has fueled progress by helping to better assess and distinguish…
A review on Deep Reinforcement Learning for Fluid Mechanics
Paul Garnier, Jonathan Viquerat, Jean Rabault +3
Deep reinforcement learning (DRL) has recently been adopted in a wide range of physics and engineering domains for its ability to solve decision-making problems that were previousl…
Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach
Jean Rabault, Alexander Kuhnle
Deep Reinforcement Learning (DRL) has recently been proposed as a methodology to discover complex Active Flow Control (AFC) strategies [Rabault, J., Kuchta, M., Jensen, A., Reglade…
The meaning of "most" for visual question answering models
Alexander Kuhnle, Ann Copestake
The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms. For the example of "most", we discuss two strategies…
How clever is the FiLM model, and how clever can it be?
Alexander Kuhnle, Huiyuan Xie, Ann Copestake
The FiLM model achieves close-to-perfect performance on the diagnostic CLEVR dataset and is distinguished from other such models by having a comparatively simple and easily transfe…
LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations
Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis +3
Reinforcement learning approaches have long appealed to the data management community due to their ability to learn to control dynamic behavior from raw system performance. Recent…
Deep learning evaluation using deep linguistic processing
Alexander Kuhnle, Ann Copestake
We discuss problems with the standard approaches to evaluation for tasks like visual question answering, and argue that artificial data can be used to address these as a complement…
ShapeWorld - A new test methodology for multimodal language understanding
Alexander Kuhnle, Ann Copestake
We introduce a novel framework for evaluating multimodal deep learning models with respect to their language understanding and generalization abilities. In this approach, artificia…