Chart patterns are significant for financial market behavior analysis. Lots of approaches have been proposed to detect specific patterns in financial time series data, most of them can be categorized as distance-based or training-based. In this paper, we applied a trainable continuous Hopfield Neural Network for financial time series pattern matching. The Perceptually Important Points (PIP) segmentation method is used as the data preprocessing procedure to reduce the fluctuation. We conducted a synthetic data experiment on both high-level noisy data and low-level noisy data. The result shows that our proposed method outperforms the Template Based (TB) and Euclidean Distance (ED) and has an advantage over Dynamic Time Warping (DTW) in terms of the processing time. That indicates the Hopfield network has a potential advantage over other distance-based matching methods.

Federated Learning (FL) learns a global model in a distributional manner, which does not require local clients to share private data. Such merit has drawn lots of attention in the interaction scenarios, where Federated Reinforcement Learning (FRL) emerges as a cross-field research direction focusing on the robust training of agents. Different from FL, the heterogeneity problem in FRL is more challenging, because the data depends on the policy of agents and the environment dynamics. FRL learns to interact under the non-stationary environment feedback, while the typical FL methods aim at handling the constant data heterogeneity. In this paper, we are among the first attempts to analyze the heterogeneity problem in FRL and propose an off-policy FRL framework. Specifically, a student-teacher-student model learning and fusion method, termed as Server-Client Collaborative Distillation (SCCD), is introduced. Unlike the traditional FL, we distill all local models on the server side for model fusion. To reduce the variance of the training, a local distillation is also conducted every time the agent receives the global model. Experimentally, we compare SCCD with a range of straightforward combinations between FL methods and RL. The results demonstrate that SCCD has a superior performance in four classical continuous control tasks with non-iid environments.