Network Risks in Markov Decision Processes.
Vassil SgurevStanislav DrangajovPublished in: CompSysTech (2020)
Keyphrases
- markov decision processes
- state space
- finite state
- reinforcement learning
- optimal policy
- transition matrices
- action sets
- policy iteration
- reachability analysis
- dynamic programming
- finite horizon
- factored mdps
- decision theoretic planning
- planning under uncertainty
- model based reinforcement learning
- reinforcement learning algorithms
- average reward
- decision making
- state and action spaces
- risk sensitive
- action space
- partially observable
- reward function
- infinite horizon
- probabilistic planning
- decision processes
- markov decision process
- np hard
- semi markov decision processes