Research output per year
Research output per year
Personal profile
Research interests
- reinforcement learning
- artificial neural networks
- evolutionary algorithms
Overview
Barry Nichols is a Lecturer in Computer Science at the University of Hertfordshire. His main research interests are in computational
intelligence, including reinforcement learning; artificial neural networks
and evolutionary algorithms. His resent research investigates the
application of these techniques to automatic generation of solutions to
continuous action-space control problems.
Fingerprint
Dive into the research topics where Barry Nichols is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
-
Genetic programming for the minimum time swing up and balance control acrobot problem
Dracopoulos, D. C. & Nichols, B. D., Oct 2017, In: Expert Systems. 34, 5, e12115.Research output: Contribution to journal › Article › peer-review
1 Citation (Scopus) -
A comparison of eligibility trace and momentum on SARSA in continuous state-and action-space
Nichols, B. D., 29 Sept 2017, 2017 9th Computer Science and Electronic Engineering (CEEC). Institute of Electrical and Electronics Engineers (IEEE), p. 55-59 5 p. 8101599Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
A comparison of action selection methods for implicit policy method reinforcement learning in continuous action-space
Nichols, B. D., 29 Jul 2016, 2016 International Joint Conference on Neural Networks (IJCNN). Institute of Electrical and Electronics Engineers (IEEE), p. 3785-3792 8 p. 7727688Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Continuous Action-Space Reinforcement Learning Methods Applied to the Minimum-Time Swing-Up of the Acrobot
Nichols, B. D., 12 Oct 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics. Institute of Electrical and Electronics Engineers (IEEE), p. 2084-2089 6 p. 7379496Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Application of Newton's method to action selection in continuous state- and action-space reinforcement learning
Nichols, B. D. & Dracopoulos, D. C., 2014, 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings. i6doc.com publication, p. 141-146 6 p. (22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
4 Citations (Scopus)