Shared Autonomy Via Deep Reinforcement Learning

Abstract

In shared autonomy, user input is combined with semi-autonomous control to achieve a common goal. The goal is often unknown ex-ante, so prior work enables agents to infer the goal from user input and assist with the task. Such methods tend to assume some combination of knowledge of the dynamics of the environment, the user's policy given their goal, and the set of possible goals the user might target, which limits their application to real-world scenarios. We propose a deep reinforcement learning framework for model-free shared autonomy that lifts these assumptions. We use human-in-the-loop reinforcement learning with neural network function approximation to learn an end-to-end mapping from environmental observation and user input to agent action values, with task reward as the only form of supervision. This approach poses the challenge of following user commands closely enough to provide the user with real-time action feedback and thereby ensure high-quality user input, but also devia

Stats

• citations112
• S2 citations—
• github stars0
• HF likes0
• heat score15.40
• arxiv keyreddy2018shared

Related papers

• To The Noise And Back: Diffusion For Shared Autonomy (2023)8.82
• Autotelic Reinforcement Learning In Multi-agent Environments (2022)0.00
• Real-world Human-robot Collaborative Reinforcement Learning (2020)9.41
• Ego-foresight: Self-supervised Learning Of Agent-aware Representations For Improved RL (2024)0.00
• Deep Reinforcement Learning For Multi-agent Interaction (2022)9.23
• Dynamic Policy Fusion For User Alignment Without Re-interaction (2024)0.00
• Self-supervised Goal-reaching Results In Multi-agent Cooperation And Exploration (2025)0.00
• Efficient Open-world Reinforcement Learning Via Knowledge Distillation And Autonomous Rule Discovery (2023)0.00