infinite Markov decision process
GPTKB entity
Statements (16)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Markov chain
|
| gptkbp:hasActionSpace |
finite or infinite
|
| gptkbp:hasApplication |
economics
operations research robotics |
| gptkbp:hasRewardFunction |
yes
|
| gptkbp:hasStateSpace |
infinite
|
| gptkbp:hasTransitionModel |
probabilistic
|
| https://www.w3.org/2000/01/rdf-schema#label |
infinite Markov decision process
|
| gptkbp:solvedBy |
dynamic programming
policy iteration value iteration |
| gptkbp:usedIn |
gptkb:reinforcement_learning
stochastic control |
| gptkbp:bfsParent |
gptkb:Markov_chain
|
| gptkbp:bfsLayer |
5
|