A New Reinforcement Learning Algorithm

@inproceedings{erban2003ANR,
  title={A New Reinforcement Learning Algorithm},
  author={Gabriela Şerban},
  year={2003}
}
The field of Reinforcement Learning, a sub-field of machine learning, represents an important direction for research in Artificial Intelligence, the way for improving an agent’s behavior, given a certain feed-back about its performance. In this paper we propose an original algorithm (URU Utility-Reward-Utility), which is a temporal difference reinforcement learning algorithm. Moreover, we design an Agent for solving a path-finding problem (searching a maze), using the URU algorithm.