Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 15 references that are in the map. First posted on arXiv 16 Oct 2023.
Builds on
9 of 15 references.
References · 9
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
- 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
- 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
- 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
- 2018Semi-parametric Topological Memory for Navigationcited by 209
- 2020MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigationcited by 95
- 2017Neural Map: Structured Memory for Deep Reinforcement Learningcited by 90
- 2015Deep Reinforcement Learning with a Natural Language Action Spacecited by 88
Built on by
Citing papers per year: 2025: 1.
1 paper.