FBAQuant — deep hedging with RL

Reinforcement-learning approach to option hedging — reward-function design for a hedging agent, grounded against the Kelly Criterion literature rather than an ad-hoc objective.

A reinforcement-learning take on option hedging: train an agent to choose hedging actions directly, rather than compute a hedge ratio analytically. The real work is in reward-function design, not the RL algorithm itself.

Free (login required): the project overview — the approach, and how it's grounded against the Kelly Criterion literature.
Members ($30/month): the actual reward-design iteration history — what changed at each stage and why, straight from the repo's own file history.

Free login  |  Become a member — $30/month  |  Already have a key?