Variance minimization of parameterized Markov decision processes.
Li XiaPublished in: Discret. Event Dyn. Syst. (2018)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- dynamic programming
- reinforcement learning
- transition matrices
- reinforcement learning algorithms
- policy iteration
- factored mdps
- partially observable
- objective function
- decision theoretic planning
- risk sensitive
- average reward
- model based reinforcement learning
- planning under uncertainty
- state and action spaces
- average cost
- decision processes
- finite horizon
- markov decision process
- infinite horizon
- action space
- reachability analysis
- reward function
- action sets
- learning algorithm
- long run
- real valued
- markov chain
- multi agent
- interval estimation