Timezone: »
Bridging The Gap between Local and Joint Differential Privacy in RL
Evrard Garcelon · Vianney Perchet · Ciara Pike-Burke · Matteo Pirotta
In this paper, we study privacy in the context of finite-horizon Markov Decision Processes. Two notions of privacy have been investigated in this setting: joint differential privacy (JDP) and local differential privacy (LDP). We show that it is possible to achieve a smooth transition in terms of privacy and regret (i.e., utility) between JDP and LDP. By leveraging shuffling techniques, we present an algorithm that, depending on the provided parameter, is able to attain any privacy/utility value in between the pure JDP and LDP guarantee.
Author Information
Evrard Garcelon (Facebook AI Research and ENSAE)
Vianney Perchet (ENS Paris-Saclay & Criteo AI Lab)
Ciara Pike-Burke (Imperial College London)
Matteo Pirotta (Facebook AI Research)
More from the Same Authors
-
2021 : Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection »
Matteo Papini · Andrea Tirinzoni · Aldo Pacchiano · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 : A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs »
Andrea Tirinzoni · Matteo Pirotta · Alessandro Lazaric -
2021 : Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret »
Jean Tarbouriech · Jean Tarbouriech · Simon Du · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2023 : Sample Complexity of Hierarchical Decompositions in Markov Decision Processes »
Arnaud Robert · Ciara Pike-Burke · Aldo Faisal -
2023 Poster: Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts »
Dirk van der Hoeven · Ciara Pike-Burke · Hao Qiu · Nicolò Cesa-Bianchi -
2023 Poster: Layered State Discovery for Incremental Autonomous Exploration »
Liyu Chen · Andrea Tirinzoni · Alessandro Lazaric · Matteo Pirotta -
2023 Poster: Delayed Feedback in Kernel Bandits »
Sattar Vakili · Danyal Ahmed · Alberto Bernacchia · Ciara Pike-Burke -
2023 Oral: Adapting to game trees in zero-sum imperfect information games »
Côme Fiegel · Pierre Menard · Tadashi Kozuno · Remi Munos · Vianney Perchet · Michal Valko -
2023 Poster: Adapting to game trees in zero-sum imperfect information games »
Côme Fiegel · Pierre Menard · Tadashi Kozuno · Remi Munos · Vianney Perchet · Michal Valko -
2023 Oral: Delayed Feedback in Kernel Bandits »
Sattar Vakili · Danyal Ahmed · Alberto Bernacchia · Ciara Pike-Burke -
2023 Poster: On Preemption and Learning in Stochastic Scheduling »
Nadav Merlis · Hugo Richard · Flore Sentenac · Corentin Odic · Mathieu Molina · Vianney Perchet -
2022 : Decentralized Learning in Online Queuing Systems »
Vianney Perchet -
2022 : Delayed Feedback in Generalised Linear Bandits Revisited »
Ciara Pike-Burke -
2022 Workshop: Responsible Decision Making in Dynamic Environments »
Virginie Do · Thorsten Joachims · Alessandro Lazaric · Joelle Pineau · Matteo Pirotta · Harsh Satija · Nicolas Usunier -
2021 Poster: Leveraging Good Representations in Linear Contextual Bandits »
Matteo Papini · Andrea Tirinzoni · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Spotlight: Leveraging Good Representations in Linear Contextual Bandits »
Matteo Papini · Andrea Tirinzoni · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Poster: Kernel-Based Reinforcement Learning: A Finite-Time Analysis »
Omar Darwiche Domingues · Pierre Menard · Matteo Pirotta · Emilie Kaufmann · Michal Valko -
2021 Spotlight: Kernel-Based Reinforcement Learning: A Finite-Time Analysis »
Omar Darwiche Domingues · Pierre Menard · Matteo Pirotta · Emilie Kaufmann · Michal Valko -
2020 Poster: No-Regret Exploration in Goal-Oriented Reinforcement Learning »
Jean Tarbouriech · Evrard Garcelon · Michal Valko · Matteo Pirotta · Alessandro Lazaric