First passage risk probability optimality for continuous time Markov decision processes.
Haifeng HuoXian WenPublished in: Kybernetika (2019)
Keyphrases
- markov decision processes
- stationary policies
- risk sensitive
- average cost
- state space
- average reward
- action sets
- optimal policy
- finite state
- optimality criterion
- optimal control
- dynamic programming
- markov decision process
- reinforcement learning
- decision theoretic planning
- markov chain
- partially observable
- transition matrices
- infinite horizon
- planning under uncertainty
- finite horizon
- policy iteration
- model based reinforcement learning
- reward function
- expected reward
- decision making
- long run
- action space
- linear program
- lot sizing
- reachability analysis
- reinforcement learning algorithms
- discounted reward
- objective function
- semi markov decision processes
- probability distribution
- probabilistic planning
- markov decision problems
- decision problems