Learning Behaviors in Agents Systems with Interactive Dynamic Influence Diagrams
- Submitting institution
-
University of Northumbria at Newcastle
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 32503173
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Proceedings of the twenty-fourth international joint conference on artificial intelligence
- First page
- 39
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- November
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
D - Computer Vision and Natural Computing (CVNC)
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work of learning policy trees for other agents in interactive dynamic influence diagrams (I-DIDs) opens up a new direction of solving recursive models for multiple agents and contributes to data-driven AI research. It provides an open learning framework for solving I-DIDs - https://bitbucket.org/rosscon/modelreduceframework. This novel research led to a successful EPSRC New Investigator Award (#EP/S011609/1; Value: £201,328; Automation and Contemplation for Model Adaptation in Multiagent Interactions). The learning technology has been adopted by Shanghai SinceMe Networking & Technology LTD (http://www.sinceme.com/about?lang=en) and improves AI game engines in commercial games with significant savings in the game development.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
