Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Should a Human Take Back Control? Optimal Delegation under Turbulent AI Risk
Haoze Yan, Julien Roze, Ved Upadhyay +2
Deploying AI systems requires deciding when to delegate tasks and when humans should intervene to monitor and mitigate risk induced by AI operations. These decisions are challengin…
cs.LG2026
Continuous-Time Reinforcement Learning for Controlled Hawkes Jump-Diffusions
Tomasz R. Bielecki, Thibaut Mastrolia, Haoze Yan
We study stochastic control of multivariate Hawkes-driven stochastic differential equations with machine learning algorithms in a non-Markovian setting. Due to the path dependence…