Deep Reinforcement Learning for Reach-Avoid-Stay Problems
On the map: Deep reinforcement learning methods → Safe and constrained RL
Abstract (arXiv)
Reach-Avoid-Stay (RAS) tasks are essential in applications where systems must safely reach a target set and remain within it under all bounded disturbances. Existing approaches either struggle to compute the maximal robust RAS set, the set of all states from which the RAS task is achievable, or are limited in handling general dynamic systems. To address these challenges, this paper proposes a two-step deep reinforcement learning framework that jointly learns the maximal robust RAS set and the corresponding control policy. The first step identifies the maximal robust control-invariant set within the target set and derives a policy that ensures the system remains within it. The second step computes the maximal robust reach-avoid (RA) set using this invariant set as the target, and it is proven that this RA set is equivalent to the maximal robust RAS set. Leveraging this result, a switching policy is constructed from the two step-wise policies, which constitutes a valid policy guaranteeing completion of the RAS task. Simulation results demonstrate that the proposed framework (1) computes the exact maximal robust RAS set in the absence of training errors, yielding the least restrictive RAS policy, and (2) identifies the RAS set with high accuracy while outperforming baseline methods on RAS tasks.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 27 references that are in the map. First posted on arXiv 3 Oct 2024.
Builds on
14 of 27 references.
References · 14
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
- 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 94
- 2020DeepReach: A Deep Learning Approach to High-Dimensional Reachabilitycited by 91
- 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
- 2021Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learningcited by 49
- 2023How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systemscited by 44
- 2022ISAACS: Iterative Soft Adversarial Actor-Critic for Safetycited by 28
- 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 27
- 2022Robot Learning of Mobile Manipulation with Reachability Behavior Priorscited by 22
- 2019A Hamilton-Jacobi Reachability-Based Framework for Predicting and Analyzing Human Motion for Safe Planningcited by 6
- 2022Infinite-Horizon Reach-Avoid Zero-Sum Games via Deep Reinforcement Learningcited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances
- 2026Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
- 2026Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark
- 2024RRLS : Robust Reinforcement Learning Suite
- 2026Winning a Won Game: Strict Reach-Avoid-Stay Control Barrier Functions for High-Dimensional Black-Box Systems ↗
- 2026LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials
- 2024Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
- 2025Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies