We present a method for learning a human understandable, executable model of an agent's behavior using observations of its interaction with the environment. By executable we ...
Andrew Guillory, Hai Nguyen, Tucker R. Balch, Char...
Most work on intelligent information agents has thus far focused on systems that are accessible through the World Wide Web. As demanding schedules prohibit people from continuous ...
This volume is intended to help advance the field of artificial neural networks along the lines of complexity present in animal brains. In particular, we are interested in examin...
Reinforcement learning (RL) algorithms provide a sound theoretical basis for building learning control architectures for embedded agents. Unfortunately all of the theory and much ...
Satinder P. Singh, Tommi Jaakkola, Michael I. Jord...
Novelty detection involves identifying novel patterns. They are not usually available during training. Even if they are, the data quantity imbalance leads to a low classification ...