Continuous-Time Reinforcement Learning for Controlled Hawkes Jump-Diffusions
By Tomasz R. Bielecki · Paper · cs.LG
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 of the memory of the Hawkes intensity, this problem does not fall within classical stochastic contro