Robust Risk-Aware Reinforcement Learning

Robust Risk-Aware Option Hedging

“…Henceforth, we call such risk measures simply as α − β risk measures. Definition 2.3 (α − β risk measure ( [12])). Let…”

“…The steps for solving the robust problem are derived in Jaimungal et al [12]. We briefly summarise the the main results here.…”

“…Theorem 5.2 (Inner Gradient Formula [12]). Under the assumptions of Theorem 2.1, let X φ c be a reordering of the realisations of X φ so that (X θ , X φ ) are comonotonic.…”

“…) is a constant. Theorem 5.3 (Outer Gradient Formula [12]). Under the same assumptions as Theorem 5.2, the outer gradient is…”

“…To safeguard agents against such uncertainties, we capitalise on advances in robust reinforcement learning (RL) as outlined by Rahimian and Mehrotra [11]. Specifically, we employ the framework presented by Jaimungal et al [12] to robustify RDEU-based strategies and apply them to the option hedging problem.…”