Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series
This addresses the challenge of control tasks on stochastic time-series data, offering incremental improvements for financial or time-series domains.
The paper tackled the problem of applying curriculum learning and imitation learning to model-free control on financial time-series, finding that curriculum learning significantly improves performance while imitation learning requires caution, with empirical results showing advantages even when tuning hyperparameters in favor of the baseline.
Curriculum learning and imitation learning have been leveraged extensively in the robotics domain. However, minimal research has been done on leveraging these ideas on control tasks over highly stochastic time-series data. Here, we theoretically and empirically explore these approaches in a representative control task over complex time-series data. We implement the fundamental ideas of curriculum learning via data augmentation, while imitation learning is implemented via policy distillation from an oracle. Our findings reveal that curriculum learning should be considered a novel direction in improving control-task performance over complex time-series. Our ample random-seed out-sample empirics and ablation studies are highly encouraging for curriculum learning for time-series control. These findings are especially encouraging as we tune all overlapping hyperparameters on the baseline -- giving an advantage to the baseline. On the other hand, we find that imitation learning should be used with caution.