Hi! PARIS Reading groups Reinforcement Learning
The Hi! PARIS reading groups propose to study a topic using scientific articles on a theoretical and a practical point of view. The reading groups are opportunities of interaction between our corporate donors and our affiliates academic teams around selected topics of interest.
Each Edition is planned for 2-4 sessions presenting one topic by the mean of 3-4 research papers. For each session: presentation of mathematical models and theoretical advances by a researcher + simulations with a Python notebook by an engineer
Registration
Please register to the event using your professional email address to get your personal conference link. Please do not share your personalised link with others, it is unique to you. You will receive an email regarding your registration status.
Edition 4 - Reinforcement Learning
For the third edition of the Hi! PARIS Reading groups, we propose an introduction to Reinforcement Learning.
More info to come in January.
Session 1/2
Tuesday 14 February, 2023 – 2.00-3.30pm (Online)
Speakers
– Charlotte Laclau, Telecom Paris – IP Paris
During this reading group, I will start we a brief introduction to the reinforcement learning setting with a focus on policy learning. I will then present GCPN (Graph Convolutional Policy Network), an approach that combines graph representation learning with reinforcement learning to generate realistic (novel) molecule graphs with desired chemical properties. The session will end with a practical application of this approach on two use cases.
Find out more info on our speaker on her personal webpage!
Paper
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation“, Jiaxuan You et al., Neurips 2018,
Other documents
– Slides of the speaker
Session 2/2
Tuesday 14 March, 2023 – 2.00-3.30pm (Online)
Speakers
– Erwan Le-Pennec, Ecole polytechnique – IP Paris
Find out more info on our speaker on his personal webpage!
Paper
Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges, Chen et al., 2022
Other documents
– Notes of the speaker in Session
– Notes of the speaker
This work has benefited from a government grant managed by the ANR under France 2030 with the reference “ANR-22-CMAS-0002”.