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

International Conference on Learning Representations (ICLR)


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 (Savva et al., 2019), 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).


Related Publications

All Publications

MICCAI - October 5, 2020

Active MR k-space Sampling with Reinforcement Learning

Luis Pineda, Sumana Basu, Adriana Romero, Roberto Calandra, Michal Drozdzal

Multimodal Video Analysis Workshop at ECCV - August 23, 2020

Audio-Visual Instance Discrimination

Pedro Morgado, Nuno Vasconcelos, Ishan Misra

ICML - November 3, 2020

Learning Near Optimal Policies with Low Inherent Bellman Error

Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill

AISTATS - November 3, 2020

A single algorithm for both restless and rested rotting bandits

Julien Seznec, Pierre Menard, Alessandro Lazaric, Michal Valko

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy