Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour
Not on the map. Why?
Abstract (arXiv)
Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. In this paper, We propose a new approach to navigation, where it is treated as a multi-task learning problem. This enables the robot to learn to behave differently in visual navigation tasks for different environments while also learning shared expertise across environments. We evaluated our approach in both simulated environments as well as real-world data. Our method allows our system to converge with a 26% reduction in training time, while also increasing accuracy.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 2 Jun 2021.
Builds on
12 of 23 references.
References · 12
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2015Trust Region Policy Optimizationcited by 2,503
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
- 2016Progressive Neural Networkscited by 1,332
- 2017Hindsight Experience Replaycited by 1,096
- 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
- 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
- 2020Agent57: Outperforming the Atari Human Benchmarkcited by 300
- 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
- 2017Distral: Robust Multitask Reinforcement Learningcited by 231
- 2019A Model-based Approach for Sample-efficient Multi-task Reinforcement Learningcited by 12
- 2019Attentive Multi-Task Deep Reinforcement Learningcited by 8
Built on by
Citing papers per year: 2022: 2.
2 papers.