Knowledge-based fast evolutionary MCTS for general video game playing
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 493
- Type
- E - Conference contribution
- DOI
-
10.1109/CIG.2014.6932868
- Title of conference / published proceedings
- IEEE Conference on Computatonal Intelligence and Games, CIG
- First page
- 1
- Volume
- -
- Issue
- -
- ISSN
- 2325-4270
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- 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
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Explores the use of Fast Evolution within Monte Carlo Tree Search (MCTS) for General Video Game AI (GVGAI). First runner-up to the best paper award on the IEEE Conference on Computational Intelligence and Games, 2014. Led to recruitment of 2 IGGI CDT PhD students [EP/L015846/1], a new collaboration with University of Maastricht, plus invitations for Lucas to give keynote talks at many conferences and workshops including IEEE CIG 2015 and was one of the papers that led to our AAAI 2015 invited paper. Underpinning work for new DSTL funded project on Statistical Forward Planning in Pommerman Variations [DSTL R1000135276].
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -