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

TL;DR

This paper introduces a neural ODE-based reinforcement learning algorithm that enhances safety and stability in human-aligned tasks by predicting movements and integrating safety constraints, demonstrated through simulations.

Contribution

It proposes a novel RL algorithm using neural ODEs combined with CBF and CLF for improved safety and stability in human-aligned tasks.

Findings

Fewer safety violations in simulations

Better sample efficiency compared to other methods

Effective goal achievement with safety guarantees

Abstract

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.