REVIEW 34 cited by
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
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
read the original abstract
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).
Forward citations
Cited by 34 Pith papers
-
POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation
POINav-Bench provides the first high-fidelity real-world benchmark for POI-goal VLN using 3DGS reconstructions of 126k m² with 163 POIs, supported by a Brain-Action framework and 70K real signage-entrance dataset.
-
Sentinel: Embodied Cooperative Spatial Reasoning and Planning
Introduces Sentinel Challenge benchmark and CoSaR framework for cooperative spatial reasoning and planning among 3-5 decentralized embodied agents across 14 city-scale scenes.
-
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
Dual-Anchoring Framework mitigates progress drift via structured instruction tokens and memory drift via landmark-centric retrospective prediction, yielding 15.2% success rate gain and 24.7% on long trajectories.
-
AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations
A goal-aligned stochastic local-path prior learned without human demos yields high navigation success and transfers from differential-drive robots to quadrupeds without retraining.
-
LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation
Distillation from frontier VLMs plus E-RLVR regularization produces a 4B local model that achieves 34.5% SR on OVON while cutting inference latency by 82.8%.
-
SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System
SurveilNav integrates robot local perception with multi-view surveillance for improved collaborative object goal navigation and reports SOTA results on HM3D.
-
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
FAST uses termination-rate-triggered virtual continuation plus masked normalized PPO loss to cut parallel RL sampling latency by ≥1.78× without biasing autonomous-driving policies.
-
Generative-Model Predictive Planning for Navigation in Partially Observable Environments
BeliefDiffusion combines diffusion models for multimodal belief distributions with MPC planning, outperforming RL and generative baselines in synthetic POMDP navigation tasks.
-
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
PSG-Nav introduces a probabilistic scene graph with multiverse sampling and an evidential calibrator to achieve new state-of-the-art success rates of 66.1%, 44.8%, and 67.9% on MP3D, HM3D, and HSSD open-vocabulary nav...
-
NavOL: Navigation Policy with Online Imitation Learning
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...
-
Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation
PLMD applies a denoising diffusion model to predict labels for unknown map regions, allowing goal localization in unexplored environments by substituting completed labels into existing navigation pipelines.
-
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
Privatar partitions VR avatar reconstruction via frequency-domain decomposition, keeping sensitive components local and offloading the rest with distribution-aware minimal perturbation noise, achieving 2.37x throughpu...
-
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Habitat-GS integrates 3D Gaussian Splatting scene rendering and Gaussian avatars into Habitat-Sim, yielding agents with stronger cross-domain generalization and effective human-aware navigation.
-
DRIVE-Nav: Directional Reasoning, Inspection, and Verification for Efficient Open-Vocabulary Navigation
Organizing zero-shot object navigation around tracked directional exits with 240° inspection and VLM verification yields 50.2% SR / 32.6% SPL on HM3D-OVON and best SPL on HM3Dv2 and MP3D.
-
ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation
ReMemNav improves zero-shot object navigation success and efficiency by integrating episodic memory and rethinking with VLMs, achieving SR/SPL gains of 1.7%/7.0% on HM3D v0.1, 18.2%/11.1% on HM3D v0.2, and 8.7%/7.9% on MP3D.
-
Memory Over Maps: 3D Object Localization Without Reconstruction
A map-free localization method stores posed RGB-D keyframes, retrieves and re-ranks them with a VLM, then fuses sparse depth for on-demand 3D target estimates, matching reconstruction-based performance on navigation b...
-
HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System
A hierarchical memory system—visual graph memory for re-visit detection plus a global instruction tracker—raises open-source zero-shot VLN success rate to 30% from 14% on R2R-CE.
-
Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigation
SIDP trains a diffusion policy for visual navigation by reward-weighting its own sampled trajectories, improving success rate and cutting inference latency.
-
Insect-inspired Visual Point-goal Navigation
A collision-triggered visual memory module steering a central-complex compass navigates point goals with no pretraining, but its path-optimization claim depends on an oracle SPL signal.
-
Insect-inspired Visual Point-goal Navigation
An insect-inspired model combining associative learning and path integration matches state-of-the-art point-goal navigation performance with orders of magnitude less computation.
-
C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
C-Nav is a continual visual navigation framework with dual-path anti-forgetting via feature distillation and replay plus adaptive sampling that outperforms baselines on a new continual object navigation benchmark whil...
-
What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework
In modular RL-based object-goal navigation, perception quality and test-time strategies dominate performance; policy architecture and observation-space choices contribute little under the tested settings.
-
FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning
FiLM-Nav fine-tunes VLMs on a mixture of simulated navigation tasks to reach state-of-the-art SPL and success on HM3D ObjectNav and OVON benchmarks with generalization to unseen categories.
-
Scalable Option Learning in High-Throughput Environments
SOL is a new hierarchical RL algorithm that reaches 35x higher throughput and outperforms flat agents when trained on 30 billion frames in NetHack while showing positive scaling.
-
Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation
SGImagineNav uses an imagined hierarchical scene graph, filled in by an LLM, that guides a robot to unseen objects and achieves 65.4% and 66.8% success on HM3D and HSSD.
-
SkeNa: Learning to Navigate Unseen Environments Based on Abstract Hand-Drawn Maps
A navigation agent can follow abstract hand-drawn sketch maps to reach goals in unseen indoor environments, backed by a new 54k-pair dataset and a model with a 105 percent relative SPL gain.
-
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
FAST uses Dynamic Parallel Sampling Alignment via virtual continuation and Scaled Mask-Padding Optimization to remove straggler bottlenecks in parallel RL, delivering 1.78x wall-clock speedup while preserving unbiasedness.
-
EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
EvolveNav adds an agentic rule memory with UCB retrieval and a memory-guided preflection module to enable continuous improvement in zero-shot object goal navigation, reporting a 10.1% success rate gain over baselines.
-
IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations
IntentNav is a spatial-visual imitation framework that infers human search intent via frontier labeling to train VLM policies for object navigation, reporting SOTA on MP3D and HM3D benchmarks with zero-shot transfer t...
-
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
Dual-Anchoring adds explicit progress tokens and retrospective landmark verification to VLN agents, cutting state drift and lifting success rate 15.2% overall with 24.7% gains on long trajectories.
-
Think before Go: Hierarchical Reasoning for Image-goal Navigation
HRNav decomposes image-goal navigation into VLM-based short-horizon planning and RL-based execution with a wandering suppression penalty to improve performance in complex unseen settings.
-
Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation
PER-based preference optimization (DPO, PPO, GRPO) reduces lyric-to-song hallucination in an audio language model, with the largest gains from DPO plus reject sampling.
-
A Large Catalog of DA White Dwarf Characteristics Using SDSS and Gaia Observations
The paper publishes the largest catalog of DA white dwarf measurements to date, using SDSS DR19 plus earlier SDSS data and Gaia, and reports a systematic offset between SDSS-V and older SDSS measurements.
-
MacroNav: Multi-Task Context Representation Learning Enables Efficient Navigation in Unknown Environments
MacroNav learns multi-scale navigation-centric representations through multi-task self-supervised learning and combines them with graph-based reinforcement learning for efficient action selection, reporting gains in s...
Discussion (0). Sign in to comment.