We propose a reinforcement learning (RL) algorithm for generating a trading strategy in a realistic setting, that includes transaction costs and factors driving the asset dynamics. We benchmark our algorithm against the analytical optimal solution, available when factors are linear and transaction costs are quadratic, showing that RL is able to mimic the optimal strategy. Then we consider a more realistic setting, including non-linear dynamics, that better describes the WTI spot prices time series. For these more general dynamics, an optimal strategy is not known and RL becomes a viable alternative. We show that on synthetic data generated from WTI spot prices, the RL agent outperforms a trader that linearizes the model to apply the theoretical optimal strategy
Giorgi, F., Herzel, S., Pigato, P. (2024). A reinforcement learning algorithm for trading commodities. APPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY, 40, 373-388 [10.1002/asmb.2825].
A reinforcement learning algorithm for trading commodities
Giorgi, Federico;Herzel, Stefano;Pigato, Paolo
2024-01-01
Abstract
We propose a reinforcement learning (RL) algorithm for generating a trading strategy in a realistic setting, that includes transaction costs and factors driving the asset dynamics. We benchmark our algorithm against the analytical optimal solution, available when factors are linear and transaction costs are quadratic, showing that RL is able to mimic the optimal strategy. Then we consider a more realistic setting, including non-linear dynamics, that better describes the WTI spot prices time series. For these more general dynamics, an optimal strategy is not known and RL becomes a viable alternative. We show that on synthetic data generated from WTI spot prices, the RL agent outperforms a trader that linearizes the model to apply the theoretical optimal strategyFile | Dimensione | Formato | |
---|---|---|---|
Appl Stoch Models Bus Ind - 2023 - Giorgi - A reinforcement learning algorithm for trading commodities.pdf
solo utenti autorizzati
Licenza:
Copyright dell'editore
Dimensione
3.48 MB
Formato
Adobe PDF
|
3.48 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.