Computational comparison of policy iteration algorithms for discounted Markov decision processes (Q1088914): Difference between revisions

This paper describes a computational comparison of the policy iteration algorithms for solving discounted Markov decision processes. It examines the different forms of iterations, reordering, extrapolation and action elimination.

0 references

Mathematics Subject Classification ID

90C40

0 references

0 references

0 references

computational comparison

0 references

policy iteration algorithms

0 references

discounted Markov decision processes

0 references

Wikidata QID

Q115104694

0 references

MaRDI profile type

MaRDI publication profile

0 references

full work available at URL

https://doi.org/10.1016/0305-0548(86)90028-6

0 references

0 references

0 references

Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems

0 references

Bounds and Transformations for Discounted Finite Markov Decision Chains

0 references

Improved iterative computation of the expected discounted return in Markov and semi-Markov chains

0 references

Computing the discounted return in markov and semi-markov chains

0 references

Technical Note—Accelerated Computation of the Expected Discounted Return in a Markov Chain

0 references

Computational comparison of value iteration algorithms for discounted Markov decision processes

0 references

Q5639278

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:1088914

@@ Property / cites work @@
+Q3266141
@@ Property / cites work: Q3266141 / rank @@
+Normal rank
@@ Property / cites work @@
+Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
+Normal rank
@@ Property / cites work @@
+Bounds and Transformations for Discounted Finite Markov Decision Chains
+Normal rank
@@ Property / cites work @@
+Improved iterative computation of the expected discounted return in Markov and semi-Markov chains
+Normal rank
@@ Property / cites work @@
+Computing the discounted return in markov and semi-markov chains
+Normal rank
@@ Property / cites work @@
+Technical Note—Accelerated Computation of the Expected Discounted Return in a Markov Chain
+Normal rank
@@ Property / cites work @@
+Computational comparison of value iteration algorithms for discounted Markov decision processes
+Normal rank
@@ Property / cites work @@
+Q5639278
@@ Property / cites work: Q5639278 / rank @@
+Normal rank