Learning to Make Predictions In Partially Observable Environments Without a Generative Model

@article{Talvitie2011LearningTM,
  title={Learning to Make Predictions In Partially Observable Environments Without a Generative Model},
  author={Erik Talvitie and Satinder P. Singh},
  journal={J. Artif. Intell. Res.},
  year={2011},
  volume={42},
  pages={353-392}
}
When faced with the problem of learning a model of a high-dimensional environment, a common approach is to limit the model to make only a restricted set of predictions, thereby simplifying the learning problem. These partial models may be directly useful for making decisions or may be combined together to form a more complete, structured model. However, in partially observable (non-Markov) environments, standard model-learning methods learn generative models, i.e. models that provide a… CONTINUE READING