Fault-Tolerant Design and Multi-Objective Model Checking for Real-Time Deep Reinforcement Learning Systems

• URL: http://arxiv.org/abs/2603.23113v1
• Date: Tue, 24 Mar 2026 12:08:06 GMT
• Title: Fault-Tolerant Design and Multi-Objective Model Checking for Real-Time Deep Reinforcement Learning Systems
• Abstract summary: Deep reinforcement learning (DRL) has emerged as a powerful paradigm for solving complex decision-making problems.<n>DRL-based systems still face significant dependability challenges due to the simulation-to-reality gap, out-of-distribution observations, and the critical impact of latency.<n>We propose a formal framework for designing and analysing real-time switching mechanisms between DRL agents and alternative controllers.
• Score: 7.759578639008443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep reinforcement learning (DRL) has emerged as a powerful paradigm for solving complex decision-making problems. However, DRL-based systems still face significant dependability challenges particularly in real-time environments due to the simulation-to-reality gap, out-of-distribution observations, and the critical impact of latency. Latency-induced faults, in particular, can lead to unsafe or unstable behaviour, yet existing fault-tolerance approaches to DRL systems lack formal methods to rigorously analyse and optimise performance and safety simultaneously in real-time settings. To address this, we propose a formal framework for designing and analysing real-time switching mechanisms between DRL agents and alternative controllers. Our approach leverages Timed Automata (TAs) for explicit switch logic design, which is then syntactically converted to a Markov Decision Process (MDP) for formal analysis. We develop a novel convex query technique for multi-objective model checking, enabling the optimisation of soft performance objectives while ensuring hard safety constraints for MDPs. Furthermore, we present MOPMC, a GPU-accelerated software tool implementing this technique, demonstrating superior scalability in both model size and objective numbers.

Related papers

• SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control [64.66285242901918]
  Shape-Aware Reinforcement Learned Model Predictive Control (SRL-MPC) is a method for safe, efficient, and adaptive navigation in crowds with heterogeneous shapes without geometry simplification.<n>A reinforcement learning framework then learns a neural policy that reads geometric separation features (GSFs) and outputs real-time MPC parameter updates.<n> Experiments in randomized crowd scenarios with arbitrary shaped robot fleets demonstrate the effectiveness, scalability, and robustness of SRL-MPC.
  arXiv  Detail & Related papers  (2026-08-21T14:46:06Z)
• Minimizing Worst-Case Weighted Latency for Multi-Robot Persistent Monitoring: Theory and RL-Based Solutions [19.90961049459541]
  We study multi-robot persistent monitoring on weighted graphs, where node weights encode monitoring priorities and edge weights encode travel.<n>The goal is to design joint robot trajectories that minimize the worst-case latency across all nodes over an infinite time horizon.
  arXiv  Detail & Related papers  (2026-05-10T16:22:48Z)
• Adaptive Linear Path Model-Based Diffusion [52.84663832658799]
  We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching linear probability path.<n>We also propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions.
  arXiv  Detail & Related papers  (2026-02-02T21:33:03Z)
• Reinforcement Learning for Control Systems with Time Delays: A Comprehensive Survey [2.3602634041257624]
  Reinforcement Learning (RL) has achieved remarkable success in the control and decision-making of complex dynamical systems.<n>Most RL algorithms rely on the Markov Decision Process assumption, which is violated in practical cyber-physical systems.<n>This paper presents a comprehensive survey of RL methods designed to address time delays in control systems.
  arXiv  Detail & Related papers  (2026-01-30T23:25:30Z)
• Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning [3.608670495432032]
  Signal temporal logic (STL) has emerged as a powerful formalism of expressing real-time constraints.<n> reinforcement learning (RL) has become an important method for solving control synthesis problems in unknown environments.<n>We propose an online reward generation method guided by the online causation monitoring of STL.
  arXiv  Detail & Related papers  (2025-10-09T02:49:28Z)
• Intersection of Reinforcement Learning and Bayesian Optimization for Intelligent Control of Industrial Processes: A Safe MPC-based DPG using Multi-Objective BO [0.0]
  Model Predictive Control (MPC)-based Reinforcement Learning (RL) offers a structured and interpretable alternative to Deep Neural Network (DNN)-based RL methods.<n>Standard MPC-RL approaches often suffer from slow convergence, suboptimal policy learning due to limited parameterization, and safety issues during online adaptation.<n>We propose a novel framework that integrates MPC-RL with Multi-Objective Bayesian Optimization (MOBO)
  arXiv  Detail & Related papers  (2025-07-14T02:31:52Z)
• Model-based controller assisted domain randomization in deep reinforcement learning: application to nonlinear powertrain control [0.0]
  This study proposes a new robust control approach using the framework of deep reinforcement learning (DRL)<n>The problem setup is modeled via the latent Markov decision process (LMDP), a set of vanilla MDPs, for a controlled system subject to uncertainties and nonlinearities.<n>Compared to traditional DRL-based controls, the proposed controller design is smarter in that we can achieve a high level of generalization ability.
  arXiv  Detail & Related papers  (2025-04-28T12:09:07Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [41.19330514054401]
  Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems to harmonize reliability and usability.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [49.362750475706235]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks.<n>We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model.<n> Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning [28.35473469490186]
  Multi-user delay constrained scheduling is important in many real-world applications including wireless communication, live streaming, and cloud computing. We propose a deep reinforcement learning (DRL) algorithm, named Recurrent Softmax Delayed Deep Double Deterministic Policy Gradient ($mathttRSD4$) $mathttRSD4$ guarantees resource and delay constraints by Lagrangian dual and delay-sensitive queues, respectively. It also efficiently tackles partial observability with a memory mechanism enabled by the recurrent neural network (RNN) and introduces user-level decomposition and node-level
  arXiv  Detail & Related papers  (2022-08-30T08:44:15Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)
• Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion [78.46388769788405]
  We introduce guided constrained policy optimization (GCPO), an RL framework based upon our implementation of constrained policy optimization (CPPO) We show that guided constrained RL offers faster convergence close to the desired optimum resulting in an optimal, yet physically feasible, robotic control behavior without the need for precise reward function tuning.
  arXiv  Detail & Related papers  (2020-02-22T10:15:53Z)

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.