A deep reinforcement learning based homeostatic system for unmanned position control
- Submitting institution
-
University of Derby
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 785921-1
- Type
- E - Conference contribution
- DOI
-
10.1145/3365109.3368780
- Title of conference / published proceedings
- Proceedings of the 6th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies
- First page
- 127
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- -
- Year of publication
- 2019
- URL
-
https://dl.acm.org/doi/10.1145/3365109.3368780
- 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)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper applies deep reinforcement learning to control of dynamic systems in unknown environments. The ability of the algorithm to identify critical states in highly uncertain environments increases the functionality of the DRL and application to dynamic control. The decision making of this DRL is explainable and can lead to new research in eXplainable AI. The functionality, transparency of decision making and potential for using fewer components means this new knowledge can will enable industrial partners increase adoption of AI techniques.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
