Markov decision processes with delays and asynchronous cost collection.
Konstantinos V. KatsikopoulosSascha E. EngelbrechtPublished in: IEEE Trans. Autom. Control. (2003)
Keyphrases
- markov decision processes
- average cost
- optimal policy
- finite state
- state space
- reinforcement learning
- policy iteration
- decision theoretic planning
- dynamic programming
- finite horizon
- infinite horizon
- transition matrices
- average reward
- reinforcement learning algorithms
- model based reinforcement learning
- total cost
- factored mdps
- state abstraction
- long run
- partially observable
- markov decision process
- reachability analysis
- decision processes
- planning under uncertainty
- risk sensitive
- reward function
- markov chain
- action sets
- initial state
- multistage
- decision diagrams
- function approximation
- objective function
- learning algorithm