mlsanityData to 7 Oct 2026

SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning

arXiv 2502.15512 ↗First posted 21 Feb 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However, real-world control systems, especially those requiring precise and reliable performance, often demand interpretability in the sense of a-priori assessments of agent behavior to identify safe or failure-prone interactions with environments. To address this limitation, this work proposes SALSA-RL (Stability Analysis in the Latent Space of Actions), a novel RL framework that models control actions as dynamic, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system, this approach enables interpretability through local stability analysis, where instantaneous growth in action-norms can be predicted before their execution. It is demonstrated that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation, SALSA-RL provides a powerful tool for advancing the design, analysis, and theoretical understanding of RL systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 73 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

41 of 73 references.

References · 41

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2016OpenAI Gymcited by 1,684
  6. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  7. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  8. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  9. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  10. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  11. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 266
  12. 2024Reinforcement learningcited by 236
29 more
  1. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  2. 2021Reinforcement Learning with Prototypical Representationscited by 179
  3. 2017Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systemscited by 125
  4. 2017Stochastic Neural Networks for Hierarchical Reinforcement Learningcited by 124
  5. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 99
  6. 2020Explainability in Deep Reinforcement Learningcited by 96
  7. 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
  8. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  9. 2021A Survey on Interpretable Reinforcement Learningcited by 70
  10. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 65
  11. 2019Neural Logic Reinforcement Learningcited by 53
  12. 2017Interpretable Policies for Reinforcement Learning by Genetic Programmingcited by 47
  13. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 45
  14. 2020Actor-Critic Reinforcement Learning for Control with Stability Guaranteecited by 39
  15. 2018Stability-certified reinforcement learning: A control-theoretic perspectivecited by 29
  16. 2021Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamicscited by 27
  17. 2024SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learningcited by 24
  18. 2021Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Controlcited by 22
  19. 2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 22
  20. 2023Concept Learning for Interpretable Multi-Agent Reinforcement Learningcited by 18
  21. 2022Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systemscited by 11
  22. 2023Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approachcited by 11
  23. 2024Koopman-Assisted Reinforcement Learningcited by 11
  24. 2023Task-Oriented Koopman-Based Control with Contrastive Encodercited by 8
  25. 2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
  26. 2024Model-based deep reinforcement learning for accelerated learning from flow simulationscited by 4
  27. 2017Symbolic Optimal Controlcited by 2
  28. 2020A Framework for Output-Feedback Symbolic Controlcited by 1
  29. 2023Interpretable Deep Reinforcement Learning for Optimizing Heterogeneous Energy Storage Systemscited by 1

Built on by

Not cited yet.