Sensitivity of constrained Markov decision processes.
Eitan AltmanAdam ShwartzPublished in: Ann. Oper. Res. (1991)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- dynamic programming
- decision theoretic planning
- reinforcement learning
- transition matrices
- decision processes
- policy iteration
- action sets
- reinforcement learning algorithms
- average cost
- sensitivity analysis
- planning under uncertainty
- average reward
- model based reinforcement learning
- risk sensitive
- action space
- finite horizon
- infinite horizon
- markov decision process
- partially observable
- reachability analysis
- state abstraction
- factored mdps
- state and action spaces
- reward function
- semi markov decision processes
- linear programming
- real time dynamic programming
- machine learning
- probabilistic planning
- discounted reward