Dynamic State Representation for Homeostatic Agents

Typ
Examensarbete för masterexamen
Master Thesis
Program
Publicerad
2018
Författare
Mäkeläinen, Fredrik
Torén, Hampus
Modellbyggare
Tidskriftstitel
ISSN
Volymtitel
Utgivare
Sammanfattning
In a reinforcement learning setting an agent learns how to behave in an environment through interactions. For complex environments, the explorable state space can easily become unmanageable, and efficient approximations are needed. The Generic Animat model (GA model), heavily influenced by biology, takes an approach utilising a dynamic graph to represent the state. This thesis is part of the Generic Animat research project at Chalmers that develops the GA model. In this thesis, we identify and implement potential improvements to the GA model and make comparisons to standard Q-learning and deep Q-learning. With the improved GA model we show that in a state space larger than 232, we see substantial performance gains compared to the original model.
Beskrivning
Ämne/nyckelord
Data- och informationsvetenskap, Computer and Information Science
Citation
Arkitekt (konstruktör)
Geografisk plats
Byggnad (typ)
Byggår
Modelltyp
Skala
Teknik / material