Feature Reinforcement Learning: Part I. Unstructured MDPs∗

@inproceedings{Marcus2009FeatureRL,
  title={Feature Reinforcement Learning: Part I. Unstructured MDPs∗},
  author={M Marcus and hutter 1. net},
  year={2009}
}
General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small finite state Markov decision processes (MDPs). Up to now, extracting the right state representations out of bare… CONTINUE READING