Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
Year of publication: |
2012
|
---|---|
Authors: | Bertsekas, Dimitri P. ; Yu, Huizhen |
Published in: |
Mathematics of operations research. - Linthicum, Md : Inst, ISSN 0364-765X, ZDB-ID 1956838. - Vol. 37.2012, 1 (13.6.), p. 66-95
|
Saved in:
Saved in favorites
Similar items by person
-
On near optimality of the set of finite-state controllers for average cost POMDP
Yu, Huizhen, (2008)
-
Error bounds for approximations from projected linear equations
Yu, Huizhen, (2010)
-
On boundedness of Q-learning iterates for stochastic shortest path problems
Yu, Huizhen, (2013)
- More ...