Mean-variance optimization of discrete time discounted Markov decision processes.
Li XiaPublished in: Autom. (2018)
Keyphrases
- markov decision processes
- finite state
- semi markov decision processes
- optimal policy
- state space
- average reward
- reinforcement learning
- transition matrices
- planning under uncertainty
- policy iteration
- average cost
- infinite horizon
- reachability analysis
- reinforcement learning algorithms
- markov chain
- finite horizon
- decision theoretic planning
- dynamic programming
- factored mdps
- model based reinforcement learning
- action space
- stationary policies
- markov decision process
- decision processes
- total reward
- partially observable
- multi agent
- discounted reward
- learning algorithm
- search space
- action sets
- state and action spaces
- risk sensitive
- multiple objectives
- multi objective
- linear program
- long run