Long-Run Rewards for Markov Automata.
Yuliya ButkovaRalf WimmerHolger HermannsPublished in: TACAS (2) (2017)
Keyphrases
- long run
- control policy
- short run
- finite state
- markov chain
- optimal policy
- markov decision processes
- reinforcement learning
- expected cost
- infinite horizon
- markov model
- finite automata
- average cost
- cellular automata
- average reward
- markov processes
- exchange rate
- inventory level
- state dependent
- queueing networks
- data mining
- short term
- scheduling problem
- customer classes