mlsanityData to 7 Oct 2026

Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations

arXiv 2401.13148 ↗First posted 23 Jan 2024cs.LG cs.RO cs.SYcited by 3

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) excels in applications such as video games, but ensuring safety as well as the ability to achieve the specified goals remains challenging when using RL for real-world problems, such as human-aligned tasks where human safety is paramount. This paper provides safety and stability definitions for such human-aligned tasks, and then proposes an algorithm that leverages neural ordinary differential equations (NODEs) to predict human and robot movements and integrates the control barrier function (CBF) and control Lyapunov function (CLF) with the actor-critic method to help to maintain the safety and stability for human-aligned tasks. Simulation results show that the algorithm helps the controlled robot to reach the desired goal state with fewer safety violations and better sample efficiency compared to other methods in a human-aligned task.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 23 Jan 2024.

Builds on

20 of 34 references.

References · 20

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  3. 2017Constrained Policy Optimizationcited by 928
  4. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  5. 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 91
  6. 2022Reachability Constrained Reinforcement Learningcited by 52
  7. 2022Uncertainty Quantification of Collaborative Detection for Self-Drivingcited by 46
  8. 2020Actor-Critic Reinforcement Learning for Control with Stability Guaranteecited by 39
  9. 2021Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safetycited by 30
  10. 2022Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithmcited by 27
  11. 2023Volumetric Semantically Consistent 3D Panoptic Mappingcited by 10
  12. 2023Physics-Regulated Deep Reinforcement Learning: Invariant Embeddingscited by 8
8 more
  1. 2022Learning Robust State Observers using Neural ODEs (longer version)cited by 6
  2. 2022QuaDUE-CCM: Interpretable Distributional Reinforcement Learning using Uncertain Contraction Metrics for Precise Quadrotor Trajectory Trackingcited by 5
  3. 2023Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Controlcited by 5
  4. 2022Safety Verification and Controller Synthesis for Systems with Input Constraintscited by 4
  5. 2019Robust Barrier Functions for a Fully Autonomous, Remotely Accessible Swarm-Robotics Testbedcited by 3
  6. 2023Physical Deep Reinforcement Learning Towards Safety Guaranteecited by 3
  7. 2023On-ramp and Off-ramp Traffic Flows Estimation Based on A Data-driven Transfer Learning Frameworkcited by 3
  8. 2023Model-Free Verification for Neural Network Controlled Systemscited by 2

Built on by

Cited by year (2026 to 7 Oct)

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

3 papers.

  1. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  2. 2024Exploring CausalWorld: Enhancing robotic manipulation via knowledge transfer and curriculum learningcited by 2
  3. 2026Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observabilitycited by 0