Reducing Risk for Assistive Reinforcement Learning Policies with Diffusion Models

TL;DR

This paper introduces a novel method using diffusion models to enhance the safety of reinforcement learning policies in assistive robotics, aiming to improve safety without extra environmental interactions.

Contribution

It proposes a diffusion model-based approach to reduce risk in RL policies for assistive robots, advancing safety without additional environment interactions.

Findings

Enhanced safety of RL policies demonstrated in simulated environments

Improved policy robustness in assistive robotics tasks

Potential for safer deployment of assistive robots

Abstract

Care-giving and assistive robotics, driven by advancements in AI, offer promising solutions to meet the growing demand for care, particularly in the context of increasing numbers of individuals requiring assistance. This creates a pressing need for efficient and safe assistive devices, particularly in light of heightened demand due to war-related injuries. While cost has been a barrier to accessibility, technological progress is able to democratize these solutions. Safety remains a paramount concern, especially given the intricate interactions between assistive robots and humans. This study explores the application of reinforcement learning (RL) and imitation learning, in improving policy design for assistive robots. The proposed approach makes the risky policies safer without additional environmental interactions. Through experimentation using simulated environments, the enhancement of the conventional RL approaches in tasks related to assistive robotics is demonstrated.