Robust Optimization for Hybrid MDPs with State-Dependent Noise.
Zahra ZamaniScott SannerKarina Valdivia DelgadoLeliane Nunes de BarrosPublished in: IJCAI (2013)
Keyphrases
- state dependent
- robust optimization
- optimal policy
- markov decision processes
- steady state
- mathematical programming
- reinforcement learning
- finite horizon
- inventory management
- stationary distribution
- queueing networks
- state space
- arrival rate
- decision problems
- markov decision process
- asymptotically optimal
- long run
- dynamic programming
- lot sizing
- multistage
- markov chain
- average cost
- continuous state
- infinite horizon
- bayesian networks
- initial state
- customer demand
- finite state
- single server
- data mining
- utility function
- probability distribution
- search algorithm
- learning algorithm