.png){kind=icon}
Return
Feature-based methods for large scale dynamic programming
.png){kind=icon}
OA
AI
DOI：10.1007/BF00114724.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We develop a methodological framework and present a few different ways in which dynamic programming and compact representations can be combined to solve large scale stochastic control problems. In particular, we develop algorithms that employ two types of feature-based compact representations; that is, representations that involve feature extraction and a relatively simple approximation architecture. We prove the convergence of these algorithms and provide bounds on the approximation error. As an example, one of these algorithms is used to generate a strategy for the game of Tetris. Furthermore, we provide a counterexample illustrating the difficulties of integrating compact representations with dynamic programming, which exemplifies the shortcomings of certain simple approaches.
Keywords:
compact representation
curse of dimensionality
dynamic programming
features
function approximation
neuro-dynamic programming
reinforcement learning
Journal
IF:
2.9
Papers:
2.7K
Citations:
3.4W
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveAn Integrated Scheduling and Retransmission Proposal for Firm Real-Time Traffic in IEEE 802.11e
PREAI
ShareSaveShareSave no more
no more