An implemented architecture for feature creation and general reinforcement learning.
Year: 2011
Type: article
Abstract: . BECCA is a brain-emulating cognition and control architecture. It was developed in order to perform general reinforcement learning, that is, to enable unmodeled systems operating in unstructured environments to perform unfamiliar tasks. It accomplishes this through complementary feature creation and reinforcement learning (RL) algorithms. Both of these algorithms are novel and have characteristics that have not been demonstrated by previously existing algorithms. This paper contains a description of BECCA and the algorithms that underlie it, illustrated with a sample implementation.
Author: Brandon Rohrer
Institution: Sandia National Laboratories
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2524898811