Abstract
Contextual skill models are learned to provide skills over a range of task parameters, often using regression across optimal task-specific policies. However, the sequential nature of the learning process is usually neglected. In this paper, we propose to use active incremental learning by selecting a task which maximizes performance improvement over entire task set. The proposed framework exploits knowledge of individual tasks accumulated in a database and shares it among the tasks using a contextual skill model. The framework is agnostic to the type of policy representation, skill model, and policy search. We evaluated the skill improvement rate in two tasks, ball-in-a-cup and basketball. In both, active selection of tasks lead to a consistent improvement in skill performance over a baseline.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019 |
Publisher | IEEE |
Pages | 1834-1839 |
Number of pages | 6 |
ISBN (Electronic) | 978-1-7281-4004-9 |
DOIs | |
Publication status | Published - 2019 |
MoE publication type | A4 Conference publication |
Event | IEEE/RSJ International Conference on Intelligent Robots and Systems - The Venetian Macao, Macau, China Duration: 4 Nov 2019 → 8 Nov 2019 https://www.iros2019.org/ |
Publication series
Name | Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems |
---|---|
Publisher | IEEE |
ISSN (Print) | 2153-0858 |
ISSN (Electronic) | 2153-0866 |
Conference
Conference | IEEE/RSJ International Conference on Intelligent Robots and Systems |
---|---|
Abbreviated title | IROS |
Country/Territory | China |
City | Macau |
Period | 04/11/2019 → 08/11/2019 |
Internet address |
Keywords
- Active incrementl learning
- Contextual skill model
- Task parameters
- Optima task-specific policies
- Learning process
- Skill improvement rate
- Skill performance
- Policy representation
- Policy search
- Ball-in-a-cup
- Basketball
- Learning (artificial intelligence)