Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis

@inproceedings{Lizotte2010EfficientRL,
  title={Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis},
  author={Daniel J. Lizotte and Michael H. Bowling and Susan A. Murphy},
  booktitle={ICML},
  year={2010}
}
We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all nondominated actions in the continuous state setting. This novel extension is appropriate for environments with continuous or finely discretized states where generalization is required, as is the case for data analysis of randomized controlled trials. 
Highly Cited
This paper has 80 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 41 extracted citations

81 Citations

01020'11'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 81 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-7 of 7 references

Multicriteria Optimization, chapter 3.Springer, second edition

  • Ehrgott, Matthias
  • 2005

Point-based value iteration: An anytime algorithm for POMDPs

  • J. Pineau, G. Gordon, S. Thrun
  • In International Joint Conference on Artificial…
  • 2003
1 Excerpt

Similar Papers

Loading similar papers…