# SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning

arXiv: https://arxiv.org/abs/2301.11520 · HTML: https://mlsanity.com/paper/2301.11520/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 41 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 30 of 38)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Decoupling Representation Learning from Reinforcement Learning](https://mlsanity.com/paper/2009.08319/) (2020)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Behavior From the Void: Unsupervised Active Pre-Training](https://mlsanity.com/paper/2103.04551/) (2021)
- [Deep Spatial Autoencoders for Visuomotor Learning](https://mlsanity.com/paper/1509.06113/) (2015)
- [Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation](https://mlsanity.com/paper/2203.15224/) (2022)
- [Self-Supervised Policy Adaptation during Deployment](https://mlsanity.com/paper/2007.04309/) (2020)
- [3D Neural Scene Representations for Visuomotor Control](https://mlsanity.com/paper/2107.04004/) (2021)
- [Unsupervised Learning of Object Keypoints for Perception and Control](https://mlsanity.com/paper/1906.11883/) (2019)
- [Representation Matters: Offline Pretraining for Sequential Decision Making](https://mlsanity.com/paper/2102.05815/) (2021)
- [Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2009.05085/) (2020)
- [Multi-view 3D Models from Single Images with a Convolutional Network](https://mlsanity.com/paper/1511.06702/) (2015)
- [VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning](https://mlsanity.com/paper/2202.10324/) (2022)

## Built on by (most cited first, 16 of 16)

- [ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation](https://mlsanity.com/paper/2403.08321/) (2024)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [GWM: Towards Scalable Gaussian World Models for Robotic Manipulation](https://mlsanity.com/paper/2508.17600/) (2025)
- [D3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement](https://mlsanity.com/paper/2309.16118/) (2023)
- [DNAct: Diffusion Guided Multi-Task 3D Policy Learning](https://mlsanity.com/paper/2403.04115/) (2024)
- [NeRFs in Robotics: A Survey](https://mlsanity.com/paper/2405.01333/) (2024)
- [MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction](https://mlsanity.com/paper/2602.03668/) (2026)
- [Reinforcement Learning with Generalizable Gaussian Splatting](https://mlsanity.com/paper/2404.07950/) (2024)
- [ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model](https://mlsanity.com/paper/2506.19842/) (2025)
- [Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset](https://mlsanity.com/paper/2312.06686/) (2023)
- [Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review](https://mlsanity.com/paper/2402.11141/) (2024)
- [Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations](https://mlsanity.com/paper/2310.17880/) (2023)
- [3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation](https://mlsanity.com/paper/2605.26500/) (2026)
- [Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter](https://mlsanity.com/paper/2503.09423/) (2025)
- [NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fields](https://mlsanity.com/paper/2411.02482/) (2024)
- [ParticleSplat: Self-supervised Object-centric Latent Particle Splatting](https://mlsanity.com/paper/2609.19463/) (2026)

## Abstract (arXiv)

As previous representations for reinforcement learning cannot effectively incorporate a human-intuitive understanding of the 3D environment, they usually suffer from sub-optimal performances. In this paper, we present Semantic-aware Neural Radiance Fields for Reinforcement Learning (SNeRL), which jointly optimizes semantic-aware neural radiance fields (NeRF) with a convolutional encoder to learn 3D-aware neural implicit representation from multi-view images. We introduce 3D semantic and distilled feature fields in parallel to the RGB radiance fields in NeRF to learn semantic and object-centric representation for reinforcement learning. SNeRL outperforms not only previous pixel-based representations but also recent 3D-aware representations both in model-free and model-based reinforcement learning.