Private Reinforcement Learning with PAC and Regret Guarantees

Authors: Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Steven Wu

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee. Our algorithm only pays for a moderate privacy cost on exploration: in comparison to the non-private bounds, the privacy parameter only appears in lower-order terms. Finally, we present lower bounds on sample complexity and regret for reinforcement learning subject to JDP.
Researcher Affiliation Collaboration 1Department of Computer Science and Engineering, University of Minnesota 2Now at Deepmind 3Microsoft Research. Correspondence to: Giuseppe Vietri <vietr002@umn.edu>, Zhiwei Steven Wu <zstevenwu@cmu.edu>, Akshay Krishnamurthy <akshaykr@microsoft.com>, Borja Balle <borja.balle@gmail.com>.
Pseudocode Yes Algorithm 2 Private Upper Confidence Bound (PUCB) [...] Algorithm 3 Priv Q(er, en, em, ε)
Open Source Code No The paper does not provide any statement or link regarding the release of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not involve empirical training or evaluation on datasets. Therefore, no information about publicly available datasets is provided.
Dataset Splits No The paper is theoretical and does not describe empirical experiments or data splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any experimental setup that would require hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any experimental setup that would require specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any empirical experimental setup, including hyperparameters or training settings.