mlsanityData to 14 Oct 2026

Analyzing Symbolic Properties for DRL Agents in Systems and Networking

arXiv 2604.04914 ↗First posted 6 Apr 2026cs.NI cs.AI cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Deep reinforcement learning (DRL) has shown remarkable performance on complex control problems in systems and networking, including adaptive video streaming, wireless resource management, and congestion control. For safe deployment, however, it is critical to reason about how agents behave across the range of system states they encounter in practice. Existing verification-based methods in this domain primarily focus on point properties, defined around fixed input states, which offer limited coverage and require substantial manual effort to identify relevant input-output pairs for analysis. In this paper, we study symbolic properties, that specify expected behavior over ranges of input states, for DRL agents in systems and networking. We present a generic formulation for symbolic properties, with monotonicity and robustness as concrete examples, and show how they can be analyzed using existing DNN verification engines. Our approach encodes symbolic properties as comparisons between related executions of the same policy and decomposes them into practically tractable sub-properties. These techniques serve as practical enablers for applying existing verification tools to symbolic analysis. Using our framework, diffRL, we conduct an extensive empirical study across three DRL-based control systems, adaptive video streaming, wireless resource management, and congestion control. Through these case studies, we analyze symbolic properties over broad input ranges, examine how property satisfaction evolves during training, study the impact of model size on verifiability, and compare multiple verification backends. Our results show that symbolic properties provide substantially broader coverage than point properties and can uncover non-obvious, operationally meaningful counterexamples, while also revealing practical solver trade-offs and limitations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 23 of its 64 references that are in the map. First posted on arXiv 6 Apr 2026.

Builds on

23 of 64 references.

References · 23

  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  2. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  3. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  4. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
  5. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 187
  6. 2019Branch and Bound for Piecewise Linear Neural Network Verificationcited by 138
  7. 2018Learning Scheduling Algorithms for Data Processing Clusterscited by 134
  8. 2019Unconstrained Monotonic Neural Networkscited by 92
  9. 2024Marabou 2.0: A Versatile Formal Analyzer of Neural Networkscited by 81
  10. 2024Neural Network Verification with Branch-and-Bound for General Nonlinearitiescited by 47
  11. 2020FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservicescited by 41
  12. 2022The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Resultscited by 39
11 more
  1. 2023The Fourth International Verification of Neural Networks Competition (VNN-COMP 2023): Summary and Resultscited by 38
  2. 2023Provably Bounding Neural Network Preimagescited by 29
  3. 2022Scalable Verification of GNN-based Job Schedulerscited by 19
  4. 2023Convex Bounds on the Softmax Function with Applications to Robustness Verificationcited by 19
  5. 2022Teal: Learning-Accelerated Optimization of WAN Traffic Engineeringcited by 13
  6. 2022Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservicescited by 12
  7. 2024Learning Optimal Deterministic Policies with Stochastic Policy Gradientscited by 12
  8. 2021Reinforcement Learning for Datacenter Congestion Controlcited by 11
  9. 2021Multi-Objective Congestion Controlcited by 2
  10. 2024AutoSpec: Automated Generation of Neural Network Specificationscited by 2
  11. 2024Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Criticscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control
  2. 2026SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networks
  3. 2026Neuro-symbolic Action Masking for Deep Reinforcement Learning
  4. 2026Sample-Efficient Neurosymbolic Deep Reinforcement Learning
  5. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
  6. 2024Analyzing Adversarial Inputs in Deep Reinforcement Learning
  7. 2026Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN Automation
  8. 2024Verification-Guided Shielding for Deep Reinforcement Learning