Recent work in algorithmic mechanism design focuses on designing mechanisms for agents with bounded rationality, modifying the constraints that must be satisfied in order to achieve incentive compatibility. StockFormer significantly outperforms existing approaches across three publicly available financial datasets in terms of portfolio returns and Sharpe ratios. The entire model is jointly trained by propagating the critic’s gradients back to the predictive coding module. The RL agent adaptively fuses these states and then executes an actor-critic algorithm in the unified state space. The predictive coding part consists of three Transformer branches with modified structures, which respectively extract effective latent states of long-/short-term future dynamics and asset relations. In this paper, we present StockFormer, a hybrid trading machine that integrates the forward modeling capabilities of predictive coding with the advantages of RL agents in policy flexibility. Typical RL-for-finance solutions directly optimize trading policies over the noisy market data, such as stock prices and trading volumes, without explicitly considering the future trends and correlations of different investment assets as we humans do.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |