Alexander Kuhnle

Publication Activity (10 Years)

Years Active: 2016-2023
Publications (10 Years): 25

Top Topics

Policy Gradient

Design Parameters

Partially Observable Environments

Question Answering

Top Venues

BlackboxNLP@ACL

Publications

Jonathan Viquerat, R. Duvigneau, P. Meliga, Alexander Kuhnle, Elie Hachem
Policy-based optimization: single-step policy gradient method seen as an evolution strategy. Neural Comput. Appl. 35 (1) (2023)
Fabio Pino, Lorenzo Schena, Jean Rabault, Alexander Kuhnle, Miguel A. Mendez
Comparative analysis of machine learning methods for active flow control. CoRR (2022)
Jonathan Viquerat, Jean Rabault, Alexander Kuhnle, Hassan Ghraieb, Aurélien Larcher, Elie Hachem
Direct shape optimization through deep reinforcement learning. J. Comput. Phys. 428 (2021)
Alexander Kuhnle, Miguel Aroca-Ouellette, Anindya Basu, Murat Sensoy, John Reid, Dell Zhang
Reinforcement Learning for Information Retrieval. SIGIR (2021)
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents. CoG (2021)
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents. CoRR (2021)
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Demonstration-Efficient Inverse Reinforcement Learning in Procedurally Generated Environments. CoG (2021)
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments. CoRR (2020)
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games. CoRR (2020)
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov
Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games. CoRR (2020)
Dell Zhang, Alexander Kuhnle, Julian Richardson, Murat Sensoy
Process Discovery for Structured Program Synthesis. CoRR (2020)
Alexander Kuhnle, Ann A. Copestake
The Meaning of "Most" for Visual Question Answering Models. BlackboxNLP@ACL (2019)
Huiyuan Xie, Tom Sherborne, Alexander Kuhnle, Ann A. Copestake
Going Beneath the Surface: Evaluating Image Captioning for Grammaticality, Truthfulness and Diversity. CoRR (2019)
Paul Garnier, Jonathan Viquerat, Jean Rabault, Aurélien Larcher, Alexander Kuhnle, Elie Hachem
A review on Deep Reinforcement Learning for Fluid Mechanics. CoRR (2019)
Alexander Kuhnle, Ann A. Copestake
What is needed for simple spatial language capabilities in VQA? CoRR (2019)
Alexander Kuhnle, Ann A. Copestake
What is needed for simple spatial language capabilities in VQA? ViGIL@NeurIPS (2019)
Jonathan Viquerat, Jean Rabault, Alexander Kuhnle, Hassan Ghraieb, Elie Hachem
Direct shape optimization through deep reinforcement learning. CoRR (2019)
Alexander Kuhnle, Huiyuan Xie, Ann A. Copestake
How clever is the FiLM model, and how clever can it be? CoRR (2018)
Alexander Kuhnle, Ann A. Copestake
The meaning of "most" for visual question answering models. CoRR (2018)
Alexander Kuhnle, Huiyuan Xie, Ann A. Copestake
How Clever Is the FiLM Model, and How Clever Can it Be? ECCV Workshops (4) (2018)
Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis, Kai Fricke, Felix Gessert, Eiko Yoneki
LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations. CoRR (2018)
Alexander Kuhnle, Ann A. Copestake
Deep learning evaluation using deep linguistic processing. CoRR (2017)
Alexander Kuhnle, Ann A. Copestake
ShapeWorld - A new test methodology for multimodal language understanding. CoRR (2017)
Ann A. Copestake, Guy Emerson, Michael Wayne Goodman, Matic Horvat, Alexander Kuhnle, Ewa Muszynska
Resources for building applications with Dependency Minimal Recursion Semantics. LREC (2016)
Yimai Fang, Haoyue Zhu, Ewa Muszynska, Alexander Kuhnle, Simone Teufel
A Proposition-Based Abstractive Summariser. COLING (2016)