State Sequences Prediction Via Fourier Transform For Representation Learning

Abstract

While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research explores the application of representation learning for data-efficient RL, e.g., learning predictive representations by predicting long-term future states. However, many existing methods do not fully exploit the structural information inherent in sequential state signals, which can potentially improve the quality of long-term decision-making but is difficult to discern in the time domain. To tackle this problem, we propose State Sequences Prediction via Fourier Transform (SPF), a novel method that exploits the frequency domain of state sequences to extract the underlying patterns in time series data for learning expressive representations efficiently. Specifically, we theoretically analyze the existence of structural information in state sequences, which

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyye2023state

Related papers

• Data-efficient Reinforcement Learning With Self-predictive Representations (2020)0.00
• Spectral Representation-based Reinforcement Learning (2025)0.00
• Functional Regularization For Reinforcement Learning Via Learned Fourier Features (2021)0.00
• Spectral Decomposition Representation For Reinforcement Learning (2022)0.00
• Learning Temporally-consistent Representations For Data-efficient Reinforcement Learning (2021)0.00
• Alphaseq: Sequence Discovery With Deep Reinforcement Learning (2018)10.07
• An Efficient, Expressive And Local Minima-free Method For Learning Controlled Dynamical Systems (2017)2.26
• Overcoming Slow Decision Frequencies In Continuous Control: Model-based Sequence Reinforcement Learning For Model-free Control (2024)0.00