Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation

Simon Hakenes; Tobias Glasmachers

Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2310.10250 v1 pith:HBG6HGIF submitted 2023-10-16 cs.LG

Simon Hakenes , Tobias Glasmachers This is my paper · ORCID

classification cs.LG

keywords actionsdeeplearningmapsreinforcementtopologicaladdressesagent

verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments

read the original abstract

This work addresses the challenge of navigating expansive spaces with sparse rewards through Reinforcement Learning (RL). Using topological maps, we elevate elementary actions to object-oriented macro actions, enabling a simple Deep Q-Network (DQN) agent to solve otherwise practically impossible environments.

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

Deep Reinforcement Learning Based Navigation with Macro Actions and Topological Maps
cs.LG 2025-04 conditional novelty 5.0 of 10

Object-based macro actions on a topological map let a plain DQN navigate multi-room scenes and outperform a random policy.

Pith tools