Partially Observable Markov Decision Process
GPTKB entity
Statements (50)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Mathematical model
|
| gptkbp:abbreviation |
gptkb:POMDP
|
| gptkbp:assumes |
Agent has incomplete information about the state
|
| gptkbp:component |
Observations
States Actions Transition function Discount factor Observation function Reward function |
| gptkbp:describes |
Decision making under uncertainty
|
| gptkbp:field |
gptkb:artificial_intelligence
Reinforcement learning Operations research |
| gptkbp:formedBy |
Mathematical notation
|
| gptkbp:generalizes |
gptkb:Markov_Decision_Process
|
| gptkbp:hasApplication |
gptkb:Autonomous_vehicles
Finance Speech recognition Game playing Resource management Medical diagnosis Dialogue systems Robot navigation |
| gptkbp:hasProperty |
gptkb:NP-hard
PSPACE-complete Computationally hard |
| https://www.w3.org/2000/01/rdf-schema#label |
Partially Observable Markov Decision Process
|
| gptkbp:originatedIn |
1960s
|
| gptkbp:relatedConcept |
gptkb:stochastic_process
gptkb:Hidden_Markov_Model Bayesian filtering Belief state |
| gptkbp:relatedTo |
gptkb:Markov_Decision_Process
|
| gptkbp:solvedBy |
gptkb:Monte_Carlo_methods
gptkb:Heuristic_search gptkb:Policy_iteration Point-based value iteration Value iteration |
| gptkbp:studiedBy |
Researchers in AI
Researchers in control theory Researchers in operations research |
| gptkbp:usedIn |
gptkb:robot
gptkb:Control_theory Natural language processing Planning Autonomous systems Medical decision making |
| gptkbp:bfsParent |
gptkb:Markov_Decision_Process
|
| gptkbp:bfsLayer |
6
|