Search Results for author: Alexander Kuhnle

Found 16 papers, 6 papers with code

Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games

no code implementations7 Dec 2020 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 environments.

Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments

no code implementations4 Dec 2020 Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov

We propose a technique based on Adversarial Inverse Reinforcement Learning which can significantly decrease the need for expert demonstrations in PCG games.

reinforcement-learning Reinforcement Learning (RL)

DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games

no code implementations3 Dec 2020 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 Reinforcement Learning (DRL).

reinforcement-learning Reinforcement Learning (RL)

Process Discovery for Structured Program Synthesis

no code implementations13 Aug 2020 Dell Zhang, Alexander Kuhnle, Julian Richardson, Murat Sensoy

A core task in process mining is process discovery which aims to learn an accurate process model from event log data.

Program Synthesis

Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning

1 code implementation26 Apr 2020 Hongwei Tang, Jean Rabault, Alexander Kuhnle, Yan Wang, Tongguang Wang

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).

Fluid Dynamics

Direct shape optimization through deep reinforcement learning

4 code implementations23 Aug 2019 Jonathan Viquerat, Jean Rabault, Alexander Kuhnle, Hassan Ghraieb, Aurélien Larcher, Elie Hachem

Deep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements.

Computational Engineering, Finance, and Science

Accelerating Deep Reinforcement Learning of Active Flow Control strategies through a multi-environment approach

4 code implementations25 Jun 2019 Jean Rabault, Alexander Kuhnle

In the case of AFC trained with Computational Fluid Mechanics (CFD) data, it was found that the CFD part, rather than the training of the Artificial Neural Network, was the limiting factor for speed of execution.

Computational Physics

The meaning of "most" for visual question answering models

no code implementations31 Dec 2018 Alexander Kuhnle, Ann Copestake

The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms.

Question Answering Visual Question Answering

How clever is the FiLM model, and how clever can it be?

no code implementations9 Sep 2018 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 transferable architecture.

LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations

4 code implementations23 Aug 2018 Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis, Kai Fricke, Felix Gessert, Eiko Yoneki

In this work, we introduce LIFT, an end-to-end software stack for applying deep reinforcement learning to data management tasks.

Management reinforcement-learning +1

Deep learning evaluation using deep linguistic processing

no code implementations WS 2018 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 to current practice.

Multimodal Deep Learning Question Answering +1

ShapeWorld - A new test methodology for multimodal language understanding

3 code implementations14 Apr 2017 Alexander Kuhnle, Ann Copestake

We introduce a novel framework for evaluating multimodal deep learning models with respect to their language understanding and generalization abilities.

Multimodal Deep Learning Test +1

Cannot find the paper you are looking for? You can Submit a new open access paper.