Reinforcement learning for ecosystems- Using explainable dynamic neural networks to train reinforcement learning agents in a simulated virtual animal ecosystem
Typ
Examensarbete för masterexamen
Program
Publicerad
2020
Författare
Hulthén, Felix
Modellbyggare
Tidskriftstitel
ISSN
Volymtitel
Utgivare
Sammanfattning
This report covers the development of an inherently explainable and dynamic neural
network for reinforcement learning in virtual animal ecosystems, based on the lifelong
learning from zero (LL0) neural network used in supervised learning. The
developed network (RLL0) is a fuzzy neural network with specialised growing and
pruning rules for an ever changing environment. Results from benchmarking against
a reference network show that RLL0 has a comparable performance while using
far fewer trainable parameters. This, combined with its adapted architecture for
visualising a learnt behaviour, shows promising future extensions to and use of the
explored algorithms for animal behavioural based biological simulations.
Beskrivning
Ämne/nyckelord
Life-long learning, reinforcement learning, fuzzy neural networks, artificial intelligence, animals