Memory Bounded Monte Carlo Tree Search
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 547
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Published by The AAAI Press, Palo Alto, California.
- First page
- 94
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- September
- Year of publication
- 2017
- 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
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper won the overall best paper award at the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), USA, 2017 (19 full papers, 19 posters accepted; around 100 submissions - [www.aaai.org/Library/AIIDE/aiide17contents.php]). It is a key result showing that our decision search algorithm (ISMCTS) can effectively use a fixed memory allocation. Our algorithm has since been used directly in commercial games will over 5 million downloads (AI Factory CEO Jef Rollason [jeff.rollason@aifactory.co.uk]) , and the ideas have been used in other commercial games, for example the Total War series by top UK games company Creative Assembly.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -