# PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators

arXiv: https://arxiv.org/abs/2406.20083 · HTML: https://mlsanity.com/paper/2406.20083/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 72 of its 86 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 30 of 72)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)

## Built on by (most cited first, 30 of 58)

- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting](https://mlsanity.com/paper/2409.10161/) (2024)
- [FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2409.16578/) (2024)
- [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation](https://mlsanity.com/paper/2507.04047/) (2025)
- [NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance](https://mlsanity.com/paper/2505.08712/) (2025)
- [TrackVLA: Embodied Visual Tracking in the Wild](https://mlsanity.com/paper/2505.23189/) (2025)
- [CaRL: Learning Scalable Planning Policies with Simple Rewards](https://mlsanity.com/paper/2504.17838/) (2025)
- [DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation](https://mlsanity.com/paper/2411.04999/) (2024)
- [ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation](https://mlsanity.com/paper/2602.11598/) (2026)
- [The Reality Gap in Robotics: Challenges, Solutions, and Best Practices](https://mlsanity.com/paper/2510.20808/) (2025)
- [Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning](https://mlsanity.com/paper/2504.00907/) (2025)
- [TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking](https://mlsanity.com/paper/2510.07134/) (2025)
- [The One RING: a Robotic Indoor Navigation Generalist](https://mlsanity.com/paper/2412.14401/) (2024)
- [SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding](https://mlsanity.com/paper/2511.04668/) (2025)
- [Do Visual Imaginations Improve Vision-and-Language Navigation Agents?](https://mlsanity.com/paper/2503.16394/) (2025)
- [FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation](https://mlsanity.com/paper/2411.09524/) (2024)
- [Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2506.05997/) (2025)
- [Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System](https://mlsanity.com/paper/2606.18112/) (2026)
- [VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory](https://mlsanity.com/paper/2601.08665/) (2026)
- [ForesightNav: Learning Scene Imagination for Efficient Exploration](https://mlsanity.com/paper/2504.16062/) (2025)
- [NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation](https://mlsanity.com/paper/2606.13494/) (2026)
- [View Invariant Learning for Vision-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2507.08831/) (2025)
- [UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories](https://mlsanity.com/paper/2512.09607/) (2025)
- [ABot-N1: Toward a General Visual Language Navigation Foundation Model](https://mlsanity.com/paper/2607.10383/) (2026)
- [Constrained Decoding for Safe Robot Navigation Foundation Models](https://mlsanity.com/paper/2509.01728/) (2025)
- [LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation](https://mlsanity.com/paper/2602.12351/) (2026)
- [CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models](https://mlsanity.com/paper/2603.22846/) (2026)

## Abstract (arXiv)

We present PoliFormer (Policy Transformer), an RGB-only indoor navigation agent trained end-to-end with reinforcement learning at scale that generalizes to the real-world without adaptation despite being trained purely in simulation. PoliFormer uses a foundational vision transformer encoder with a causal transformer decoder enabling long-term memory and reasoning. It is trained for hundreds of millions of interactions across diverse environments, leveraging parallelized, multi-machine rollouts for efficient training with high throughput. PoliFormer is a masterful navigator, producing state-of-the-art results across two distinct embodiments, the LoCoBot and Stretch RE-1 robots, and four navigation benchmarks. It breaks through the plateaus of previous work, achieving an unprecedented 85.5% success rate in object goal navigation on the CHORES-S benchmark, a 28.5% absolute improvement. PoliFormer can also be trivially extended to a variety of downstream applications such as object tracking, multi-object navigation, and open-vocabulary navigation with no finetuning.