English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper proposes a novel scheme for the watermarking of Deep ReinforcementLearning (DRL) policies. This scheme provides a mechanism for the integrationof a unique identifier within the policy in the form of its response to adesignated sequence of state transitions, while incurring minimal impact on thenominal performance of the policy. The applications of this watermarking schemeinclude detection of unauthorized replications of proprietary policies, as wellas enabling the graceful interruption or termination of DRL activities byauthorized entities. We demonstrate the feasibility of our proposal viaexperimental evaluation of watermarking a DQN policy trained in the Cartpoleenvironment.

Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies