Abstract
An autonomous agent placed without any prior knowledge in an environment without goals or a reward function will need to develop a model of that environment using an unguided approach by discovering patters occurring in its observations. We expand on a prior algorithm which allows an agent to achieve that by learning clusters in probability distributions of one-dimensional sensory variables and propose a novel quadtree-based algorithm for two dimensions. We then evaluate it in a dynamic continuous domain involving a ball being thrown onto uneven terrain, simulated using a physics engine. Finally, we put forward criteria which can be used to evaluate a domain model without requiring goals and apply them to our work. We show that adding two-dimensional rules to the algorithm improves the model and that such models can be transferred to similar but previously-unseen environments.
Original language | English |
---|---|
Title of host publication | International Conference on Development and Learning and Epigenetic Robotics 2013 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 1-6 |
Number of pages | 6 |
DOIs | |
Publication status | Published - 20 Aug 2013 |
Event | International Conference on Development and Learning and Epigenetic Robotics 2013 - Osaka, Japan., United Kingdom Duration: 19 Aug 2013 → 21 Aug 2013 |
Conference
Conference | International Conference on Development and Learning and Epigenetic Robotics 2013 |
---|---|
Country/Territory | United Kingdom |
City | Osaka, Japan. |
Period | 19/08/13 → 21/08/13 |