Robust Synchronization in Markov Decision Processes.
Laurent DoyenThierry MassartMahsa ShirmohammadiPublished in: CoRR (2014)
Keyphrases
- markov decision processes
- finite state
- state space
- policy iteration
- optimal policy
- transition matrices
- reinforcement learning
- dynamic programming
- average reward
- reachability analysis
- reinforcement learning algorithms
- infinite horizon
- partially observable
- decision theoretic planning
- decision processes
- average cost
- action sets
- model based reinforcement learning
- finite horizon
- planning under uncertainty
- markov decision process
- factored mdps
- state and action spaces
- semi markov decision processes
- reward function
- risk sensitive
- state abstraction
- real time dynamic programming