VDCBPI: an Approximate Scalable Algorithm for Large POMDPs

  title={VDCBPI: an Approximate Scalable Algorithm for Large POMDPs},
  author={Pascal Poupart and Craig Boutilier},
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability: the curse of dimensionality and the policy space complexity. This paper describes a new algorithm (VDCBPI) that mitigates both sources of intractability by combining the Value Directed Compression (VDC) technique [13] with Bounded Policy Iteration (BPI) [14]. The scalability of VDCBPI is demonstrated on synthetic… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 113 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 71 extracted citations

Scalable solutions of interactive POMDPs using generalized and bounded policy iteration

Autonomous Agents and Multi-Agent Systems • 2014
View 9 Excerpts
Highly Influenced

Agent Interactions in Decentralized Environments

Andrew Arnt, Stephen Ambrogio, +6 authors Louis Theran
View 6 Excerpts
Highly Influenced

113 Citations

Citations per Year
Semantic Scholar estimates that this publication has 113 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 15 references

A point-based POMDP algorithm for robot planning

IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 • 2004
View 4 Excerpts
Highly Influenced

Point-based value iteration: an anytime algorithm for POMDPs

J. Pineau, G. Gordon, S. Thrun
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…