Pith. sign in

REVIEW 1 cited by

Auxiliary Tasks Speed Up Learning PointGoal Navigation

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 2007.04561 v2 pith:BLKEMQAP submitted 2020-07-09 cs.CV cs.LGcs.RO

classification cs.CVcs.LGcs.RO
keywords auxiliarytasksframesdd-ppoefficiencyimproveslearningmethod
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment. Wijmans et al. showed that this task is solvable but their method is computationally prohibitive, requiring 2.5 billion frames and 180 GPU-days. In this work, we develop a method to significantly increase sample and time efficiency in learning PointNav using self-supervised auxiliary tasks (e.g. predicting the action taken between two egocentric observations, predicting the distance between two observations from a trajectory,etc.).We find that naively combining multiple auxiliary tasks improves sample efficiency,but only provides marginal gains beyond a point. To overcome this, we use attention to combine representations learnt from individual auxiliary tasks. Our best agent is 5.5x faster to reach the performance of the previous state-of-the-art, DD-PPO, at 40M frames, and improves on DD-PPO's performance at 40M frames by 0.16 SPL. Our code is publicly available at https://github.com/joel99/habitat-pointnav-aux.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigation

    cs.RO 2026-01 conditional novelty 6.0 of 10

    SIDP trains a diffusion policy for visual navigation by reward-weighting its own sampled trajectories, improving success rate and cutting inference latency.

Pith tools