Semi-Markov Decision Processes
GPTKB entity
Statements (27)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:logic
decision process |
gptkbp:abbreviation |
SMDP
|
gptkbp:application |
control theory
finance robotics queueing systems |
gptkbp:distinctFrom |
Markov Decision Processes: allows variable time between transitions
|
gptkbp:feature |
generalized state transitions
variable transition times |
gptkbp:field |
gptkb:reinforcement_learning
operations research stochastic processes |
gptkbp:generalizes |
gptkb:Markov_Decision_Processes
|
gptkbp:hasComponent |
states
actions rewards transition probabilities sojourn times |
https://www.w3.org/2000/01/rdf-schema#label |
Semi-Markov Decision Processes
|
gptkbp:introducedIn |
1950s
|
gptkbp:relatedTo |
gptkb:Markov_Decision_Processes
Markov processes |
gptkbp:solvedBy |
dynamic programming
reinforcement learning algorithms |
gptkbp:bfsParent |
gptkb:Markov_Decision_Processes
|
gptkbp:bfsLayer |
7
|