By leveraging so-called deep neural networks and using unprecedented computing power, the reinforcement learning community has obtained remarkable achievements these last years. They drew the attention and interest of many towards RL. Indeed, a vast amount of practical problems seem to fit the RL setting. During this talk, I will present a set of our recent works dealing with various fields of applications (agriculture, agro-ecology, soft robotics). I will also discuss the practical difficulties we faced, and the experimental methodological issues that we currently meet in RL, and some solutions.
Philippe Preux is a professor in Computer Science at the Université de Lille, France. He has been active in research in artificial intelligence for 30 years now, mostly dealing with machine learning and data mining in the last 2 decades, especially reinforcement learning. He has been the head of the SequeL research group at Inria/CNRS/Université de Lille since 2006, a group now renamed Scool. His research ranges from fundamental algorithmic and methodological questions to applications of reinforcement learning in collaboration with companies. Philippe currently focuses his efforts on applications related to health or sustainable development. He has hosted ICML 2015, and co-organized various scientific events such as the European Workshop on Reinforcement Learning in 2008 and 2018, as well as the Reinforcement Learning Summer School in 2019.
The talk was delivered during ML in PL Conference 2023 as a part of Contributed Talks. The conference was organized by a non-profit NGO called ML in PL Association.
ML in PL Association website: mlinpl.org/
ML In PL Conference 2023 website: conference2023.mlinpl.org/
ML In PL Conference 2024 website: conference.mlinpl.org/
---
ML in PL Association was founded based on the experiences in organizing of the ML in PL Conference (formerly PL in ML), the ML in PL Association is a non-profit organization devoted to fostering the machine learning community in Poland and Europe and promoting a deep understanding of ML methods. Even though ML in PL is based in Poland, it seeks to provide opportunities for international cooperation.
17 июн 2024
