Privacy-preserving reinforcement learning

Authors:
Jun Sakuma;Shigenobu Kobayashi;Rebecca N. Wright
Affiliations:
Tokyo Institute of Technology, Yokohama, Japan;Tokyo Institute of Technology, Yokohama, Japan;Rutgers University, Piscataway, NJ
Venue:
Proceedings of the 25th international conference on Machine learning
Year:
2008

Citing 11
Cited 2

Reinforcement Learning

Reinforcement Learning
Distributed Value Functions

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Foundations of Cryptography: Volume 2, Basic Applications

Foundations of Cryptography: Volume 2, Basic Applications
Cross channel optimized marketing by reinforcement learning

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Privacy preserving learning in negotiation

Proceedings of the 2005 ACM symposium on Applied computing
Privacy-preserving distributed k-means clustering over arbitrarily partitioned data

Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
Privacy-preserving SVM using nonlinear kernels on horizontally partitioned data

Proceedings of the 2006 ACM symposium on Applied computing
Privacy-preserving boosting

Data Mining and Knowledge Discovery
Fairplay—a secure two-party computation system

SSYM'04 Proceedings of the 13th conference on USENIX Security Symposium - Volume 13
How to generate and exchange secrets

SFCS '86 Proceedings of the 27th Annual Symposium on Foundations of Computer Science
Large-scale k-means clustering with user-centric privacy preservation

PAKDD'08 Proceedings of the 12th Pacific-Asia conference on Advances in knowledge discovery and data mining

Link analysis for private weighted graphs

Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Privacy preserving semi-supervised learning for labeled graphs

ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider the problem of distributed reinforcement learning (DRL) from private perceptions. In our setting, agents' perceptions, such as states, rewards, and actions, are not only distributed but also should be kept private. Conventional DRL algorithms can handle multiple agents, but do not necessarily guarantee privacy preservation and may not guarantee optimality. In this work, we design cryptographic solutions that achieve optimal policies without requiring the agents to share their private information.