Koopman-based Generalization Of Deep Reinforcement Learning With Application To Wireless Communications

Abstract

Deep Reinforcement Learning (DRL) is a key machine learning technology driving progress across various scientific and engineering fields, including wireless communication. However, its limited interpretability and generalizability remain major challenges. In supervised learning, generalizability is commonly evaluated through the generalization error using information-theoretic methods. In DRL, the training data is sequential and not independent and identically distributed (i.i.d.), rendering traditional information-theoretic methods unsuitable for generalizability analysis. To address this challenge, this paper proposes a novel analytical method for evaluating the generalizability of DRL. Specifically, we first model the evolution of states and actions in trained DRL algorithms as unknown discrete, stochastic, and nonlinear dynamical functions. Then, we employ a data-driven identification method, the Koopman operator, to approximate these functions, and propose two interpretable repres

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytermehchi2025koopman

Related papers

• Generalization In Reinforcement Learning For Radio Access Networks (2025)0.00
• Measuring And Characterizing Generalization In Deep Reinforcement Learning (2018)9.76
• A Survey Analyzing Generalization In Deep Reinforcement Learning (2024)0.00
• A Survey On Deep Reinforcement Learning-based Approaches For Adaptation And Generalization (2022)0.00
• Assessing Generalization In Deep Reinforcement Learning (2018)0.00
• Dynamics Generalization Via Information Bottleneck In Deep Reinforcement Learning (2020)0.00
• Cooperative Multi-agent Reinforcement Learning For Low-level Wireless Communication (2018)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00