Strategic planning under uncertainties via constrained Markov Decision Processes.
Xu Chu DingAlessandro PintoAmit SuranaPublished in: ICRA (2013)
Keyphrases
- markov decision processes
- strategic planning
- state space
- finite state
- reinforcement learning
- optimal policy
- dynamic programming
- policy iteration
- average cost
- transition matrices
- e government
- reachability analysis
- partially observable
- factored mdps
- decision theoretic planning
- finite horizon
- average reward
- machine learning
- model based reinforcement learning
- risk sensitive
- reinforcement learning algorithms
- planning under uncertainty
- decision making
- semi markov decision processes
- infinite horizon
- decision processes
- learning algorithm
- markov decision process
- data mining
- state and action spaces
- supply chain