Changing the Environment Based on Empowerment as Intrinsic Motivation
- Submitting institution
-
University of Hertfordshire
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13599873
- Type
- D - Journal article
- DOI
-
10.3390/e16052789
- Title of journal
- Entropy
- Article number
- -
- First page
- 2789
- Volume
- 16
- Issue
- 5
- ISSN
- 1099-4300
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- 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
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- First environment-changing algorithm in a Minecraft-type scenario, based on purely intrinsic motivation measures. First use of simple Monte-Carlo sampling for efficient estimation of empowerment in deterministic worlds at comparatively large depth. Triggered significant cascade of publications on automated environment construction avoiding human-designed measures. Horizon 2020 grant 705643 (InterCoGaM, "Information Theoretic Evaluation of Random Content Generation in Games", Marie Curie Individual Fellowship 2016-2019, 251,857 EUR) for Christoph Salge crucially based on the success of this work.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -