Publications

2023

  • Policy-based optimization: single-step policy gradient method seen as an evolution strategy. January 2023. Jonathan Viquerat, Régis Duvigneau, Philippe Meliga, Alexander Kuhnle and Elie Hachem. Neural Computing and Applications 35 (1). [paper] [arxiv]

2022

  • Deep Reinforcement Learning applied to Active Flow Control. Upcoming. Jean Rabault and Alexander Kuhnle. [preprint]

2021

  • Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents. August 2021. Alessandro Sestini, Alexander Kuhnle and Andrew D. Bagdanov. 3rd IEEE Conference on Games (CoG 2021), Copenhagen (Denmark). [arxiv]

  • A review on deep reinforcement learning for fluid mechanics. July 2021. Paul Garnier, Jonathan Viquerat, Jean Rabault, Aurélien Larcher, Alexander Kuhnle and Elie Hachem. Computers & Fluids 225, 104973. [pdf] [arxiv]

  • Direct shape optimization through deep reinforcement learning. March 2021. Jonathan Viquerat, Jean Rabault, Alexander Kuhnle, Hassan Ghraieb, Aurélien Larcher and Elie Hachem. Journal of Computational Physics 428, 110080. [pdf] [arxiv]

  • Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments. February/August 2021. Alessandro Sestini, Alexander Kuhnle and Andrew D. Bagdanov. Workshop on Reinforcement Learning in Games (AAAI 2021), virtual. 3rd IEEE Conference on Games (CoG 2021), Copenhagen (Denmark). [pdf] [arxiv]

  • Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games. February 2021. Alessandro Sestini, Alexander Kuhnle and Andrew D. Bagdanov. Workshop on Reinforcement Learning in Games (AAAI 2021), virtual. [pdf] [arxiv]

2020

  • Process Discovery for Structured Program Synthesis. August 2020. Dell Zhang, Alexander Kuhnle, Julian Richardson and Murat Sensoy. [arxiv]

  • Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning. May 2020. Hongwei Tang, Jean Rabault, Alexander Kuhnle, Yan Wang and Tongguang Wang. Physics of Fluids 32, 053605. [pdf] [arxiv]

  • Going Beneath the Surface: Evaluating Image Captioning for Grammaticality, Truthfulness and Diversity. February 2020. Huiyuan Xie, Tom Sherborne, Alexander Kuhnle and Ann Copestake. Workshop on Evaluating Evaluation of AI Systems (AAAI 2020), in New York (USA). [arxiv]

  • Evaluating visually grounded language capabilities using microworlds. January 2020. Alexander Kuhnle. PhD Thesis. [pdf] [techreport]

2019

  • What is needed for simple spatial language capabilities in VQA?. December 2019. Alexander Kuhnle and Ann Copestake. Workshop on Visually Grounded Interaction and Language (NeurIPS 2019), in Vancouver (Canada). [arxiv] [poster]

  • DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games. October 2019. Alessandro Sestini, Alexander Kuhnle and Andrew D. Bagdanov. Workshop on Experimental AI in Games (AIIDE 2019), in Atlanta (USA). [pdf] [arxiv]

  • Accelerating Deep Reinforcement Learning of Active Flow Control strategies through a multi-environment approach. September 2019. Jean Rabault and Alexander Kuhnle. Physics of Fluids 31, 094105. [pdf] [arxiv]

  • The meaning of “most” for visual question answering models. August 2019. Alexander Kuhnle and Ann Copestake. Proceedings of the 2nd edition of the BlackboxNLP Workshop (ACL 2019), in Florence (Italy). [pdf] [arxiv] [poster]

2018

  • How clever is the FiLM model, and how clever can it be?. September 2018. Alexander Kuhnle, Huiyuan Xie and Ann Copestake. Proceedings of the Workshop on Shortcomings in Vision and Language (ECCV 2018), in Munich (Germany). [pdf] [arxiv] [poster]

  • LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations. August 2018. Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis, Kai Fricke, Felix Gessert and Eiko Yoneki. [arxiv]

  • Deep learning evaluation using deep linguistic processing. June 2018. Alexander Kuhnle and Ann Copestake. Proceedings of the Workshop on Generalization in the Age of Deep Learning (NAACL 2018), in New Orleans (USA). [pdf] [arxiv] [poster]

2017

  • Artificial microworlds and deep linguistic processing for evaluating language understanding. June 2017. Alexander Kuhnle and Ann Copestake. Machine Learning Summer School (MLSS 2017), in Tübingen (Germany). [poster]

  • ShapeWorld: A new test methodology for multimodal language understanding. April 2017. Alexander Kuhnle and Ann Copestake. [arxiv] [github]

2016

  • A proposition-based abstractive summariser. December 2016. Yimai Fang, Haoyue Zhu, Ewa Muszyńska, Alexander Kuhnle and Simone Teufel. Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016), in Osaka (Japan). [pdf]

  • Evaluating multi-modal deep learning systems with micro-worlds. November 2016. Alexander Kuhnle and Ann Copestake. Cambridge Language Sciences Annual Symposium 2016, in Cambridge (UK). [abstract] [poster]

  • Investigating the effect of controlled context choice in distributional semantics. August 2016. Alexander Kuhnle. ESSLLI Workshop on Distributional Semantics and Linguistic Theory (DSALT 2016), in Bolzano (Italy). [abstract] [poster]

  • Resources for building applications with Dependency Minimal Recursion Semantics. May 2016. Ann Copestake, Guy Emerson, Michael Wayne Goodman, Matic Horvat, Alexander Kuhnle and Ewa Muszyńska. Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), in Portorož (Slovenia). [pdf] [github]

Talks

  • Reinforcement Learning for Information Retrieval. Full-day tutorial at multiple venues, together with Miguel Aroca-Ouellette, Anindya Basu, John Reid, Dell Zhang and Murat Sensoy. [website] [github]
    • International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021). July 2021, online event. [proceedings] [website]
    • European Conference on Information Retrieval (ECIR 2021). March 2021, online event. [website]
    • Search Solutions. November 2020, online event. [website]

  • Tensorforce: building an applied reinforcement learning framework using TensorFlow. January 2020. Invited talk, at Google London (UK). [slides]

  • Deep learning evaluation using ShapeWorld. July 2019. DELPH-IN Annual Meeting, at University of Cambridge (UK). [slides]

  • Tensorforce: a library for applied reinforcement learning. April 2019. Bosch Research Campus, in Renningen (Germany).

  • Deep reinforcement learning for controlling complex systems. December 2018. University of Oslo, in Oslo (Norway). [slides]

  • “Unit-testing” deep learning with synthetic data for more informative evaluation. Oktober 2018. Montreal Institute for Learning Algorithms (MILA), in Montreal (Canada). [slides]

  • “Unit-testing” deep learning with synthetic data for more informative evaluation. June 2018. Cambridge Language Sciences Research Symposium for Early-Career Researchers, in Cambridge (UK). [slides]

  • The potential of synthetic data for more informative evaluation in Visual Question Answering. May 2018. NLIP Seminar Series, at the Computer Laboratory, University of Cambridge (UK). [slides]

  • ShapeWorld for automatic language generation in a closed-world domain. August 2017. DELPH-IN Annual Meeting, at University of Oslo (Norway). [slides]

  • Natural language quantifier learning for multi-modal deep neural nets. February 2017. Research visit to the Center for Mind/Brain Sciences (CIMeC), University of Trento (Italy). Collaboration with Raffaella Bernardi, Aurélie Herbelot, Sandro Pezzelle and Ionut Sorodoc. [slides]

  • GraphLang: A DMRS graph description language. June 2016. DELPH-IN Annual Meeting, at Stanford University (USA). [slides]