Spectral Representation-based Reinforcement Learning

• URL: http://arxiv.org/abs/2512.15036v1
• Date: Wed, 17 Dec 2025 02:54:42 GMT
• Title: Spectral Representation-based Reinforcement Learning
• Authors: Chenxiao Gao, Haotian Sun, Na Li, Dale Schuurmans, Bo Dai,
• Abstract summary: We introduce the perspective of spectral representations as a solution to difficulties in reinforcement learning.<n>We show how to construct spectral representations for transition operators that possess latent variable structures or energy-based structures.<n>We also provably extend this spectral view to partially observable MDPs.
• Score: 42.78610854620513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful approximations such as neural networks offer great expressiveness, they often present theoretical ambiguities, suffer from optimization instability and exploration difficulty, and incur substantial computational costs in practice. In this paper, we introduce the perspective of spectral representations as a solution to address these difficulties in RL. Stemming from the spectral decomposition of the transition operator, this framework yields an effective abstraction of the system dynamics for subsequent policy optimization while also providing a clear theoretical characterization. We reveal how to construct spectral representations for transition operators that possess latent variable structures or energy-based structures, which implies different learning methods to extract spectral representations from data. Notably, each of these learning methods realizes an effective RL algorithm under this framework. We also provably extend this spectral view to partially observable MDPs. Finally, we validate these algorithms on over 20 challenging tasks from the DeepMind Control Suite, where they achieve performances comparable or superior to current state-of-the-art model-free and model-based baselines.

Related papers

• Deep Unfolding: Recent Developments, Theory, and Design Guidelines [99.63555420898554]
  This article provides a tutorial-style overview of deep unfolding, a framework that transforms optimization algorithms into structured, trainable ML architectures.<n>We review the foundations of optimization for inference and for learning, introduce four representative design paradigms for deep unfolding, and discuss the distinctive training schemes that arise from their iterative nature.
  arXiv  Detail & Related papers  (2025-12-03T13:16:35Z)
• Fourier Neural Operators Explained: A Practical Perspective [75.12291469255794]
  The Fourier Neural Operator (FNO) has become the most influential and widely adopted due to its elegant spectral formulation.<n>This guide aims to establish a clear and reliable framework for applying FNOs effectively across diverse scientific and engineering fields.
  arXiv  Detail & Related papers  (2025-12-01T08:56:21Z)
• Learning dynamically inspired invariant subspaces for Koopman and transfer operator approximation [0.0]
  We use general operator and representational learning to approximate transfer and Koopman operators.<n>Specifically, we machine-learn orthonormal basis functions that are dynamically tailored to the system.<n>We illustrate our approach with examples that showcase the retrieval of spectral properties from the estimated operator.
  arXiv  Detail & Related papers  (2025-05-08T09:32:39Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Spectral Decomposition Representation for Reinforcement Learning [100.0424588013549]
  We propose an alternative spectral method, Spectral Decomposition Representation (SPEDER), that extracts a state-action abstraction from the dynamics without inducing spurious dependence on the data collection policy. A theoretical analysis establishes the sample efficiency of the proposed algorithm in both the online and offline settings. An experimental investigation demonstrates superior performance over current state-of-the-art algorithms across several benchmarks.
  arXiv  Detail & Related papers  (2022-08-19T19:01:30Z)
• A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning [55.048010996144036]
  We show that under some noise assumption, we can obtain the linear spectral feature of its corresponding Markov transition operator in closed-form for free. We propose Spectral Dynamics Embedding (SPEDE), which breaks the trade-off and completes optimistic exploration for representation learning by exploiting the structure of the noise.
  arXiv  Detail & Related papers  (2021-11-22T19:24:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.