Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces

January 30, 2019 ยท Declared Dead ยท ๐Ÿ› Neural Information Processing Systems

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Baoxiang Wang, Nidhi Hegde arXiv ID 1901.10634 Category stat.ML: Machine Learning (Stat) Cross-listed cs.AI, cs.LG Citations 71 Venue Neural Information Processing Systems Last Checked 3 months ago
Abstract
We consider differentially private algorithms for reinforcement learning in continuous spaces, such that neighboring reward functions are indistinguishable. This protects the reward information from being exploited by methods such as inverse reinforcement learning. Existing studies that guarantee differential privacy are not extendable to infinite state spaces, as the noise level to ensure privacy will scale accordingly to infinity. Our aim is to protect the value function approximator, without regard to the number of states queried to the function. It is achieved by adding functional noise to the value function iteratively in the training. We show rigorous privacy guarantees by a series of analyses on the kernel of the noise space, the probabilistic bound of such noise samples, and the composition over the iterations. We gain insight into the utility analysis by proving the algorithm's approximate optimality when the state space is discrete. Experiments corroborate our theoretical findings and show improvement over existing approaches.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning (Stat)

๐Ÿ”ฎ ๐Ÿ”ฎ The Ethereal

Layer Normalization

Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton

stat.ML ๐Ÿ› arXiv ๐Ÿ“š 12.0K cites 9 years ago

Died the same way โ€” ๐Ÿ‘ป Ghosted