Information capture and reuse strategies in Monte Carlo Tree Search, with applications to games of hidden information
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 546
- Type
- D - Journal article
- DOI
-
10.1016/j.artint.2014.08.002
- Title of journal
- Artificial Intelligence
- Article number
- -
- First page
- 92
- Volume
- 217
- Issue
- -
- ISSN
- 0004-3702
- Open access status
- Out of scope for open access requirements
- Month of publication
- December
- Year of publication
- 2014
- 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
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes the ICARUS framework: deepening understanding and enhancing creativity in Monte Carlo Tree Search algorithms for searching complex game trees. We embedded the ideas in a commercial card game with over 5 million installs (CEO [jeff.rollason@aifactory.co.uk]). The paper is the culmination of a large collaborative project (?1.5m EPSRC funding - EP/I001964/1, EP/H049061/1&2, EP/H048588/1) and was a key paper in securing a CDT in Games Research (EP/L015846/1 (?5.6m) and EP/S022325/1 (?6.4m) - Cowling is PI). David Silver, technical lead of DeepMind?s AlphaGo project, was external examiner for Whitehouse?s PhD.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -