Learning Visual Routines with Reinforcement Learning

  title={Learning Visual Routines with Reinforcement Learning},
  author={Andrew K Mccallum},
Reinforcement learning is an ideal framework to learn visual routines since the routines are made up of sequences of actions. However, such algorithms must be able to handle the hidden state (perceptual aliasing) that results from visual routine’s purposefully narrowed attention. The U-Tree algorithm successfully learns visual routines for a complex driving task in which the agent makes eye movements and executes deictic actions in order to weave in and out of traffic on a four-laned highway… CONTINUE READING
2 Citations
18 References
Similar Papers


Publications citing this paper.
Showing 1-2 of 2 extracted citations


Publications referenced by this paper.
Showing 1-10 of 18 references

The partigame algorithm for variable resolution reinforcement learning in multidimensional state spaces

  • A. W. Moore
  • Advances of Neural Information Processing Systems…
  • 1993
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…