# Learning a Universal Human Prior for Dexterous Manipulation from Human Preference

arXiv: https://arxiv.org/abs/2304.04602 · HTML: https://mlsanity.com/paper/2304.04602/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 49 references that are in the map.
- First posted on arXiv 10 Apr 2023.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Reward learning from human preferences and demonstrations in Atari](https://mlsanity.com/paper/1811.06521/) (2018)
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [A System for General In-Hand Object Re-Orientation](https://mlsanity.com/paper/2111.03043/) (2021)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy](https://mlsanity.com/paper/2303.00938/) (2023)
- [Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2206.08686/) (2022)
- [In-Hand Object Rotation via Rapid Motor Adaptation](https://mlsanity.com/paper/2210.04887/) (2022)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [Few-Shot Preference Learning for Human-in-the-Loop RL](https://mlsanity.com/paper/2212.03363/) (2022)
- [Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube](https://mlsanity.com/paper/2202.10448/) (2022)
- [Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation](https://mlsanity.com/paper/2203.13251/) (2022)
- [Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences](https://mlsanity.com/paper/2006.14091/) (2020)
- [Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations](https://mlsanity.com/paper/2207.05053/) (2022)
- [Residual Reinforcement Learning from Demonstrations](https://mlsanity.com/paper/2106.08050/) (2021)
- [Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps](https://mlsanity.com/paper/2209.11221/) (2022)
- [Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2211.11602/) (2022)
- [Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation](https://mlsanity.com/paper/1904.13041/) (2019)

## Built on by (most cited first, 10 of 10)

- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [Is RLHF More Difficult than Standard RL?](https://mlsanity.com/paper/2306.14111/) (2023)
- [GraspXL: Generating Grasping Motions for Diverse Objects at Scale](https://mlsanity.com/paper/2403.19649/) (2024)
- [ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation](https://mlsanity.com/paper/2309.03891/) (2023)
- [Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm](https://mlsanity.com/paper/2503.03796/) (2025)
- [Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective](https://mlsanity.com/paper/2312.00054/) (2023)
- [Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey](https://mlsanity.com/paper/2506.00098/) (2025)
- [On The Global Convergence Of Online RLHF With Neural Parametrization](https://mlsanity.com/paper/2410.15610/) (2024)
- [The Power of Combined Modalities in Interactive Robot Learning](https://mlsanity.com/paper/2405.07817/) (2024)
- [Variable-Friction In-Hand Manipulation for Arbitrary Objects via Diffusion-Based Imitation Learning](https://mlsanity.com/paper/2503.02738/) (2025)

## Abstract (arXiv)

Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands. Scripting policies from scratch is intractable due to the high-dimensional control space, and training policies with reinforcement learning (RL) and manual reward engineering can also be hard and lead to unnatural motions. Leveraging the recent progress on RL from Human Feedback, we propose a framework that learns a universal human prior using direct human preference feedback over videos, for efficiently tuning the RL policies on 20 dual-hand robot manipulation tasks in simulation, without a single human demonstration. A task-agnostic reward model is trained through iteratively generating diverse polices and collecting human preference over the trajectories; it is then applied for regularizing the behavior of polices in the fine-tuning stage. Our method empirically demonstrates more human-like behaviors on robot hands in diverse tasks including even unseen tasks, indicating its generalization capability.