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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recently, there has been a surge in interest in safe and robust techniqueswithin reinforcement learning (RL). Current notions of risk in RL fail tocapture the potential for systemic failures such as abrupt stoppages fromsystem failures or surpassing of safety thresholds and the appropriateresponsive controls in such instances. We propose a novel approach to riskminimisation within RL in which, in addition to taking actions that maximiseits expected return, the controller learns a policy that is robust againststoppages due to an adverse event such as an abrupt failure. The results of thepaper cover fault-tolerant control in \textit{worst-case scenarios} underrandom stopping and optimal stopping, all in unknown environments. Bydemonstrating that the class of problems is represented by a variant ofstochastic games, we prove the existence of a solution which is a unique fixedpoint equilibrium of the game and characterise the optimal controllerbehaviour. We then introduce a value function approximation algorithm thatconverges to the solution through simulation in unknown environments.

Cutting Your Losses: Learning Fault-Tolerant Control and Optimal Stopping under Adverse Risk