Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Efficient Robot Learning via Interaction with Humans
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a data-efficient approach for robots to learn partner objectives through interaction with humans rather than relying on large demonstration datasets.
Problem
Modeling human or multi-agent partners and estimating their objectives for human-robot collaboration, where learning from demonstrations is data-hungry and demonstrations can be unreliable.
Approach
Learn partner models and objectives from interaction with the partner instead of from demonstrations, to reduce data requirements. The abstract is truncated, so the specific mechanism is not stated.
Closest papers by meaning
- Towards Better Robot Learners: Leveraging Implicit and Explicit Human Feedback Together in Human Robot Interactions (AAAI 2025 · similarity 0.91)
- Learning to Interactively Learn and Assist (AAAI 2020 · similarity 0.88)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.85)
- GUIDE: Real-Time Human-Shaped Agents (NeurIPS 2024 · similarity 0.85)
- Making AI Policies Transparent to Humans through Demonstrations (AAAI 2024 · similarity 0.85)
- ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.