Privacy Preserving Reinforcement Learning over Distributed Datasets
As the IoT is becoming increasingly popular, the possibility to exchange data between a group, or fleet, of similar devices arises. This allows institutions to share data about a specific control task to boost learning processes.
However, such data sets are often confidential and cannot be shared in their raw form. We propose a privacy-preserving reinforcement learning technique that enables knowledge transfer among agents based on a peer-to-peer encryption protocol.
Passionate about Mathematics and Technology, I undertook a master course in Mathematics, AI and Cryptography two years ago at the ULB after a 20 years career on financial markets in London. Currently, I am working on a drug discovery AI project for a consortium of pharmaceutical laboratories and researching Privacy Preserving AI at the KUL.