mlsanityData to 14 Oct 2026

DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames

arXiv 1911.00357 ↗First posted 1 Nov 2019cs.CV cs.AI cs.LGcited by 362

Not on the map. Why?

Cited by 28 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present Decentralized Distributed Proximal Policy Optimization (DD-PPO), a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever stale), making it conceptually simple and easy to implement. In our experiments on training virtual robots to navigate in Habitat-Sim, DD-PPO exhibits near-linear scaling -- achieving a speedup of 107x on 128 GPUs over a serial implementation. We leverage this scaling to train an agent for 2.5 Billion steps of experience (the equivalent of 80 years of human experience) -- over 6 months of GPU-time training in under 3 days of wall-clock time with 64 GPUs. This massive-scale training not only sets the state of art on Habitat Autonomous Navigation Challenge 2019, but essentially solves the task --near-perfect autonomous navigation in an unseen environment without access to a map, directly from an RGB-D camera and a GPS+Compass sensor. Fortuitously, error vs computation exhibits a power-law-like distribution; thus, 90% of peak performance is obtained relatively early (at 100 million steps) and relatively cheaply (under 1 day with 8 GPUs). Finally, we show that the scene understanding and navigation policies learned can be transferred to other navigation tasks -- the analog of ImageNet pre-training + task-specific fine-tuning for embodied AI. Our model outperforms ImageNet pre-trained CNNs on these transfer tasks and can serve as a universal resource (all models and code are publicly available).

Key facts. Cited by 362 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 56; 2022: 68; 2023: 75; 2024: 56; 2025: 48; 2026: 58.

362 papers.

Sort:

By area:

  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  2. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  3. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  4. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  5. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  6. 2022SQA3D: Situated Question Answering in 3D Scenescited by 314
  7. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
  8. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  9. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 239
  10. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 228
  11. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 218
  12. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
38 more
  1. 2021Simple but Effective: CLIP Embeddings for Embodied AIcited by 191
  2. 2022ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddingscited by 178
  3. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 176
  4. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  5. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 167
  6. 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 165
  7. 2022The Unsurprising Effectiveness of Pre-Trained Vision Models for Controlcited by 155
  8. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  9. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  10. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 129
  11. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 122
  12. 2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 121
  13. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 117
  14. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 117
  15. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 117
  16. 2022Habitat-Matterport 3D Semantics Datasetcited by 110
  17. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 109
  18. 2022Navigating to Objects in the Real Worldcited by 106
  19. 2023HomeRobot: Open-Vocabulary Mobile Manipulationcited by 106
  20. 2021Visual Room Rearrangementcited by 102
  21. 2022SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learningcited by 95
  22. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 94
  23. 2024GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigationcited by 94
  24. 2023PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNavcited by 93
  25. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  26. 2023Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planningcited by 89
  27. 2022Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigationcited by 86
  28. 2023Large Language Models as Generalizable Policies for Embodied Taskscited by 86
  29. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  30. 2022Offline Visual Representation Learning for Embodied Navigationcited by 75
  31. 2021Auxiliary Tasks and Exploration Enable ObjectNavcited by 74
  32. 2024HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigationcited by 71
  33. 2023OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNavcited by 70
  34. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 67
  35. 2024OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Modelscited by 67
  36. 2025Robust Autonomy Emerges from Self-Playcited by 67
  37. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 66
  38. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 65

50 most cited of 362 All 362 (JSON)