Pith. sign in

REVIEW 16 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.20083 v1 pith:OAHEUKHQ submitted 2024-06-28 cs.RO cs.CV

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

classification cs.RO cs.CV
keywords navigationpoliformertrainedtransformeracrossmasterfulobjectresults
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

    cs.CV 2026-05 accept novelty 8.0

    Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO p...

  2. Beyond Isolation: A Unified Benchmark for General-Purpose Navigation

    cs.RO 2026-05 unverdicted novelty 7.0

    OmniNavBench is a unified benchmark for general-purpose navigation featuring composite multi-skill instructions, support for humanoid, quadrupedal and wheeled robots, and 1779 human teleoperated trajectories across 17...

  3. LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

    cs.CV 2026-02 conditional novelty 7.0

    LangMap is a human-verified navigation benchmark with 18K tasks spanning scene-, room-, region-, and instance-level goals in real-world 3D scans, covering 414 object categories.

  4. ABot-N1: Toward a General Visual Language Navigation Foundation Model

    cs.CV 2026-07 conditional novelty 6.0

    ABot-N1 decouples navigation into a slow CoT-plus-pixel-goal reasoner and a fast waypoint controller, claiming state-of-the-art results on five VLN benchmarks and releasing two new urban navigation benchmarks.

  5. ABot-N1: Toward a General Visual Language Navigation Foundation Model

    cs.CV 2026-07 conditional novelty 6.0

    A slow–fast VLN model that routes five navigation tasks through CoT plus image-space pixel goals reaches SOTA on established and new urban benchmarks, including 77.3% POI arrival.

  6. ABot-N1: Toward a General Visual Language Navigation Foundation Model

    cs.CV 2026-07 unverdicted novelty 6.0

    ABot-N1 decouples VLN into a slow CoT reasoner that outputs pixel goals and a fast action expert, claiming large SOTA gains on urban POI and multi-task navigation.

  7. SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System

    cs.RO 2026-06 unverdicted novelty 6.0

    SurveilNav integrates robot local perception with multi-view surveillance for improved collaborative object goal navigation and reports SOTA results on HM3D.

  8. NavOL: Navigation Policy with Online Imitation Learning

    cs.RO 2026-05 unverdicted novelty 6.0

    NavOL collects expert trajectory labels online from a global planner during policy rollouts in simulation to train a diffusion navigation policy, mitigating distribution shift and improving performance on visual navig...

  9. Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation

    cs.RO 2026-05 unverdicted novelty 6.0

    SAGE trains agents in physics-grounded semantic abstractions via RL with asymmetric clipping, achieving 53.21% LLM-Match Success on A-EQA (+9.7% over baseline) and encouraging physical robot transfer.

  10. VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning

    cs.RO 2025-05 conditional novelty 6.0

    VLA-RL applies online RL to pretrained VLAs, yielding a 4.5% gain over strong baselines on 40 LIBERO manipulation tasks and matching commercial models like π₀-FAST.

  11. Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

    cs.RO 2024-12 unverdicted novelty 6.0

    Uni-NaVid unifies diverse embodied navigation tasks into one video-based vision-language-action model trained on 3.6 million samples from four sub-tasks, achieving state-of-the-art performance on benchmarks and real-w...

  12. Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System

    cs.RO 2026-06 unverdicted novelty 5.0

    Qwen-RobotNav introduces a parameterized navigation model supporting multiple task modes and controllable observation parameters, trained on 15.6M samples with vision-language co-training to achieve SOTA results on be...

  13. Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System

    cs.RO 2026-06 unverdicted novelty 5.0

    Qwen-RobotNav provides a parameterized navigation model trained on 15.6M samples with vision-language co-training that achieves SOTA results on benchmarks and zero-shot transfer to real robots.

  14. AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning

    cs.RO 2026-06 unverdicted novelty 5.0

    AllDayNav encodes scene dynamics into a large model's parameters via RL and a multimodal memory, achieving near-100% success rates in lifelong navigation and outperforming map-based and VLM baselines.

  15. Learning Category-level Last-meter Navigation from RGB Demonstrations of a Single-instance

    cs.RO 2025-12 conditional novelty 5.0

    An RGB-only imitation-learning policy trained on one chair generalizes to unseen chairs and environments for last-meter base positioning, though reported success depends on an added heuristic stopping rule and a 0.3 m...

  16. SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

    cs.RO 2025-03 unverdicted novelty 5.0

    SafeVLA applies constrained reinforcement learning via CMDP min-max optimization to VLAs, cutting safety violation costs by 83.58% while preserving task success on long-horizon mobile manipulation tasks.