Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction

@inproceedings{Sutton2011HordeAS,
  title={Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction},
  author={Richard S. Sutton and Joseph Modayil and Michael Delp and Thomas Degris and Patrick M. Pilarski and Adam White and Doina Precup},
  booktitle={AAMAS},
  year={2011}
}
Maintaining accurate world knowledge in a complex and changing environment is a perennial problem for robots and other artificial intelligence systems. Our architecture for addressing this problem, called Horde, consists of a large number of independent reinforcement learning sub-agents, or demons. Each demon is responsible for answering a single predictive or goal-oriented question about the world, thereby contributing in a factored, modular way to the system’s overall knowledge. The questions… CONTINUE READING

Citations

Publications citing this paper.

315 Citations

050100'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 315 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

A model for the encoding of experiential information

  • J. D. Becker
  • In Computer Models of Thought and Language,
  • 1973
Highly Influential
6 Excerpts

Monte-Carlo tree search. PhD thesis, Dutch Research School for Information and Knowledge Systems

  • Chaslot, G. M. J-B
  • 2010
1 Excerpt

Convergent temporaldifference learning with arbitrary smooth function approximation

  • H. R. Maei, Szepesvári, +4 authors R. S. Sutton
  • In Advances in Neural Information Processing…
  • 2009
1 Excerpt

Similar Papers

Loading similar papers…