Markov Decision Process

GPTKB entity

Statements (53)
Predicate Object
gptkbp:instanceOf gptkb:logic
gptkb:stochastic_process
gptkbp:abbreviation gptkb:MDP
gptkbp:component gptkb:public_policy
states
actions
rewards
transition probabilities
gptkbp:field gptkb:artificial_intelligence
gptkb:reinforcement_learning
decision theory
operations research
gptkbp:generalizes Markov chain
gptkbp:hasApplication gptkb:machine_learning
gptkb:navigation
autonomous systems
control theory
economics
finance
game theory
healthcare
marketing
planning
queueing theory
robotics
telecommunications
resource management
customer service
resource allocation
supply chain management
traffic control
energy management
scheduling
inventory control
maintenance planning
network optimization
portfolio optimization
medical decision making
resource scheduling
https://www.w3.org/2000/01/rdf-schema#label Markov Decision Process
gptkbp:introducedIn 1950s
gptkbp:namedAfter gptkb:Andrey_Markov
gptkbp:property gptkb:Markov_property
gptkbp:relatedTo gptkb:Partially_Observable_Markov_Decision_Process
gptkb:Bellman_equation
gptkb:stochastic_game
gptkbp:solvedBy dynamic programming
policy iteration
value iteration
gptkbp:usedFor modeling decision making
sequential decision problems
gptkbp:bfsParent gptkb:MDP
gptkbp:bfsLayer 5