finite Markov decision process
GPTKB entity
Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Markov chain
|
| gptkbp:abbreviation |
finite MDP
|
| gptkbp:describedBy |
Richard S. Sutton and Andrew G. Barto's book 'Reinforcement Learning: An Introduction'
|
| gptkbp:hasActionSpaceType |
finite
|
| gptkbp:hasApplication |
gptkb:artificial_intelligence
control theory operations research robotics |
| gptkbp:hasComponent |
action space
discount factor reward function state space transition probability function |
| gptkbp:hasProperty |
gptkb:Markov_property
|
| gptkbp:hasStateSpaceType |
finite
|
| https://www.w3.org/2000/01/rdf-schema#label |
finite Markov decision process
|
| gptkbp:solvedBy |
gptkb:Monte_Carlo_methods
dynamic programming temporal-difference learning |
| gptkbp:usedIn |
gptkb:reinforcement_learning
|
| gptkbp:bfsParent |
gptkb:Markov_chain
|
| gptkbp:bfsLayer |
5
|