Deep Bellman Hedging
Hans Buehler, Phillip Murray, Ben Wood

TL;DR
This paper introduces a reinforcement learning algorithm for optimal portfolio hedging that accounts for trading costs, liquidity constraints, and complex financial instruments, providing adaptable and risk-aware hedging strategies.
Contribution
It develops a novel actor-critic reinforcement learning method for hedging with derivatives, incorporating realistic market frictions and enabling real-time, risk-adjusted hedging without re-training.
Findings
The algorithm effectively hedges diverse portfolios using historic data.
It accounts for trading costs and liquidity constraints in the hedging process.
The trained model generalizes to new market states without re-training.
Abstract
We present an actor-critic-type reinforcement learning algorithm for solving the problem of hedging a portfolio of financial instruments such as securities and over-the-counter derivatives using purely historic data. The key characteristics of our approach are: the ability to hedge with derivatives such as forwards, swaps, futures, options; incorporation of trading frictions such as trading cost and liquidity constraints; applicability for any reasonable portfolio of financial instruments; realistic, continuous state and action spaces; and formal risk-adjusted return objectives. Most importantly, the trained model provides an optimal hedge for arbitrary initial portfolios and market states without the need for re-training. We also prove existence of finite solutions to our Bellman equation, and show the relation to our vanilla Deep Hedging approach
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
