Hierarchical Reinforcement Learning for Temporal Pattern Prediction
This work addresses prediction tasks in finance and autonomous driving, but it is incremental as it builds on existing HRL methods.
The paper tackled temporal sequence prediction by applying hierarchical reinforcement learning (HRL) to stock price and steering angle prediction, resulting in significant improvements in training speed, stability, and accuracy over standard RL.
In this work, we explore the use of hierarchical reinforcement learning (HRL) for the task of temporal sequence prediction. Using a combination of deep learning and HRL, we develop a stock agent to predict temporal price sequences from historical stock price data and a vehicle agent to predict steering angles from first person, dash cam images. Our results in both domains indicate that a type of HRL, called feudal reinforcement learning, provides significant improvements to training speed and stability and prediction accuracy over standard RL. A key component to this success is the multi-resolution structure that introduces both temporal and spatial abstraction into the network hierarchy.