@phdthesis{190,
  author = {Michael Waltham and Deshen Moodley and Anban Pillay},
  title = {Q-Cog: A Q-Learning Based Cognitive Agent  Architecture for Complex 3D Virtual Worlds},
  abstract = {Intelligent cognitive agents requiring a high level of adaptability should contain min- imal initial data and be able to autonomously gather new knowledge from their own experiences. 3D virtual worlds provide complex environments in which autonomous software agents may learn and interact. In many applications within this domain, such as video games and virtual reality, the environment is partially observable and agents must make decisions and react in real-time. Due to the dynamic nature of virtual worlds, adaptability is of great importance for virtual agents. The Reinforce- ment Learning paradigm provides a mechanism for unsupervised learning that allows agents to learn from their own experiences in the environment. In particular, the Q- Learning algorithm allows agents to develop an optimal action-selection policy based on their environment experiences. This research explores the potential of cognitive architectures utilizing Reinforcement Learning whereby agents may contain a library of action-selection policies within virtual environments. The proposed cognitive archi- tecture, Q-Cog, utilizes a policy selection mechanism to develop adaptable 3D virtual agents. Results from experimentation indicates that Q-Cog provides an effective basis for developing adaptive self-learning agents for 3D virtual worlds.},
  year = {2018},
  volume = {MSc},
  publisher = {Durban University},
}