Efficient exploration with Double Uncertain Value Networks

@article{Moerland2017EfficientEW,
  title={Efficient exploration with Double Uncertain Value Networks},
  author={Thomas M. Moerland and Joost Broekens and Catholijn M. Jonker},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.10789}
}
This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the distribution of the returns (return uncertainty). We identify methods to learn these distributions with deep neural networks, where we estimate parametric uncertainty with Bayesian… CONTINUE READING
10
Twitter Mentions

Citations

Publications citing this paper.
SHOWING 1-10 OF 10 CITATIONS