# Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations

arXiv: https://arxiv.org/abs/2404.17521 · HTML: https://mlsanity.com/paper/2404.17521/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 58 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [Human-to-Robot Imitation in the Wild](https://mlsanity.com/paper/2207.09450/) (2022)
- [Ditto: Building Digital Twins of Articulated Objects from Interaction](https://mlsanity.com/paper/2202.08227/) (2022)
- [AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System](https://mlsanity.com/paper/2307.04577/) (2023)
- [A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms](https://mlsanity.com/paper/1907.03146/) (2019)
- [GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts](https://mlsanity.com/paper/2211.05272/) (2022)
- [UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy](https://mlsanity.com/paper/2303.00938/) (2023)

## Built on by (most cited first, 24 of 24)

- [RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2407.04689/) (2024)
- [RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning](https://mlsanity.com/paper/2504.18904/) (2025)
- [VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2503.07135/) (2025)
- [ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models](https://mlsanity.com/paper/2506.16211/) (2025)
- [Towards Generalist Robot Learning from Internet Video: A Survey](https://mlsanity.com/paper/2404.19664/) (2024)
- [GWM: Towards Scalable Gaussian World Models for Robotic Manipulation](https://mlsanity.com/paper/2508.17600/) (2025)
- [A Survey of Embodied Learning for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2408.11537/) (2024)
- [Decompositional Neural Scene Reconstruction with Generative Diffusion Prior](https://mlsanity.com/paper/2503.14830/) (2025)
- [GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding](https://mlsanity.com/paper/2411.19626/) (2024)
- [PhysPart: Physically Plausible Part Completion for Interactable Objects](https://mlsanity.com/paper/2408.13724/) (2024)
- [Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation](https://mlsanity.com/paper/2406.14235/) (2024)
- [Dexterous Manipulation through Imitation Learning: A Survey](https://mlsanity.com/paper/2504.03515/) (2025)
- [MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes](https://mlsanity.com/paper/2412.11457/) (2024)
- [TACO: Taming Diffusion for in-the-wild Video Amodal Completion](https://mlsanity.com/paper/2503.12049/) (2025)
- [G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior](https://mlsanity.com/paper/2510.12099/) (2025)
- [GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill](https://mlsanity.com/paper/2504.04191/) (2025)
- [PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention](https://mlsanity.com/paper/2512.03724/) (2025)
- [FLEX: A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulation](https://mlsanity.com/paper/2503.13418/) (2025)
- [TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning](https://mlsanity.com/paper/2509.11839/) (2025)
- [Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge](https://mlsanity.com/paper/2510.08316/) (2025)
- [VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances](https://mlsanity.com/paper/2608.05215/) (2026)
- [RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment](https://mlsanity.com/paper/2603.29419/) (2026)
- [DailyArt: Discovering Articulation from Single Static Images via Latent Dynamics](https://mlsanity.com/paper/2604.07758/) (2026)
- [CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2605.21854/) (2026)

## Abstract (arXiv)

Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, modern methods (e.g., VIP and R3M) still face significant hurdles, notably the domain gap among robotic embodiments and the sparsity of successful task executions within specific action spaces, resulting in misaligned and ambiguous task representations. We introduce Ag2Manip (Agent-Agnostic representations for Manipulation), a framework aimed at surmounting these challenges through two key innovations: a novel agent-agnostic visual representation derived from human manipulation videos, with the specifics of embodiments obscured to enhance generalizability; and an agent-agnostic action representation abstracting a robot's kinematics to a universal agent proxy, emphasizing crucial interactions between end-effector and object. Ag2Manip's empirical validation across simulated benchmarks like FrankaKitchen, ManiSkill, and PartManip shows a 325% increase in performance, achieved without domain-specific demonstrations. Ablation studies underline the essential contributions of the visual and action representations to this success. Extending our evaluations to the real world, Ag2Manip significantly improves imitation learning success rates from 50% to 77.5%, demonstrating its effectiveness and generalizability across both simulated and physical environments.