Complex, dynamic environments pose a number of challenges for learning agents. A complex environment has many objects, events, and potential tasks to be learned which results in a very large search space. The size of the search space increases exponentially since a potential state can be any combination of all possible states for any object. This exponential increase can have a dramatic effect on the ability of the learning agent to achieve a specific task.
CITATION STYLE
Merrick, K. E., & Maher, M. L. (2009). Curious Characters for Games in Complex, Dynamic Environments. In Motivated Reinforcement Learning (pp. 151–170). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-89187-1_8
Mendeley helps you to discover research relevant for your work.