Active Policy Learning for Robot Planning and Exploration under Uncertainty

  title={Active Policy Learning for Robot Planning and Exploration under Uncertainty},
  author={Ruben Martinez-Cantin and Nando de Freitas and Arnaud Doucet and Jos{\'e} A. Castellanos},
  booktitle={Robotics: Science and Systems},
This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested in the domain of robot navigation and exploration under uncertainty, where the expected cost is a function of the belief state (filtering distribution). This filtering distribution is in turn nonlinear and subject to discontinuities, which arise because constraints in the robot motion and control models. As a result, the expected… CONTINUE READING
Highly Cited
This paper has 155 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 92 extracted citations

155 Citations

Citations per Year
Semantic Scholar estimates that this publication has 155 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 33 references

Simulationbased optimal sensor scheduling with application to observer trajectory planning

  • S. Singh, N. Kantas, A. Doucet, B. N. Vo, R. J. Evans
  • IEEE Conference on Decision and Control and…
  • 2005
2 Excerpts

Similar Papers

Loading similar papers…