mlsanityData to 7 Oct 2026

Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications

arXiv 2210.01162 ↗First posted 3 Oct 2022cs.RO cs.AI cs.FLcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper explores continuous-time control synthesis for target-driven navigation to satisfy complex high-level tasks expressed as linear temporal logic (LTL). We propose a model-free framework using deep reinforcement learning (DRL) where the underlying dynamic system is unknown (an opaque box). Unlike prior work, this paper considers scenarios where the given LTL specification might be infeasible and therefore cannot be accomplished globally. Instead of modifying the given LTL formula, we provide a general DRL-based approach to satisfy it with minimal violation. To do this, we transform a previously multi-objective DRL problem, which requires simultaneous automata satisfaction and minimum violation cost, into a single objective. By guiding the DRL agent with a sampling-based path planning algorithm for the potentially infeasible LTL task, the proposed approach mitigates the myopic tendencies of DRL, which are often an issue when learning general LTL tasks that can have long or infinite horizons. This is achieved by decomposing an infeasible LTL formula into several reach-avoid sub-tasks with shorter horizons, which can be trained in a modular DRL architecture. Furthermore, we overcome the challenge of the exploration process for DRL in complex and cluttered environments by using path planners to design rewards that are dense in the configuration space. The benefits of the presented approach are demonstrated through testing on various complex nonlinear systems and compared with state-of-the-art baselines. The Video demonstration can be found here:https://youtu.be/jBhx6Nv224E.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 26 of its 49 references that are in the map. First posted on arXiv 3 Oct 2022.

Builds on

26 of 49 references.

References · 26

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 307
  3. 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 183
  4. 2017Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learningcited by 81
  5. 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
  6. 2018Learning Navigation Behaviors End-to-End with AutoRLcited by 70
  7. 2019Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?cited by 66
  8. 2019Joint Inference of Reward Machines and Policies for Reinforcement Learningcited by 56
  9. 2014A Learning Based Approach to Control Synthesis of Markov Decision Processes for Linear Temporal Logic Specificationscited by 49
  10. 2015Control Contraction Metrics: Convex and Intrinsic Criteria for Nonlinear Feedback Designcited by 38
  11. 2021Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logiccited by 38
  12. 2020Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfactioncited by 22
14 more
  1. 2021FaSTrack: a Modular Framework for Real-Time Motion Planning and Guaranteed Safe Trackingcited by 15
  2. 2020Optimal Probabilistic Motion Planning with Potential Infeasible LTL Constraintscited by 14
  3. 2021Neural Network Verification in Controlcited by 14
  4. 2019An Abstraction-Free Method for Multi-Robot Temporal Logic Optimal Control Synthesiscited by 11
  5. 2022Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specificationscited by 11
  6. 2022Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewardscited by 11
  7. 2022Accelerated Reinforcement Learning for Temporal Logic Control Objectivescited by 9
  8. 2017Model Predictive Control for Signal Temporal Logic Specificationcited by 8
  9. 2020What to Do When You Can't Do It All: Temporal Logic Planning with Soft Temporal Logic Constraintscited by 7
  10. 2020Minimum-Violation Planning for Autonomous Systems: Theoretical and Practical Considerationscited by 7
  11. 2020Receding Horizon Control Based Online Motion Planning with Partially Infeasible LTL Specificationscited by 3
  12. 2021Automata-based Optimal Planning with Relaxed Specificationscited by 2
  13. 2014On the Minimal Revision Problem of Specification Automatacited by 1
  14. 2018Minimum Violation Control Synthesis on Cyber-Physical Systems under Attackscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2024Adaptive Reward Design for Reinforcement Learningcited by 5
  2. 2023Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specificationscited by 3
  3. 2024Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Explorationcited by 3
  4. 2023On Reducing Undesirable Behavior in Deep Reinforcement Learning Modelscited by 0
  5. 2026Legislating World-Model-Based Planning with Legal Reasoningcited by 0