Estimation and adaptive control of span-contracting Markov decision processes.
Gerhard HübnerPublished in: Kybernetika (1991)
Keyphrases
- markov decision processes
- adaptive control
- reinforcement learning
- optimal policy
- control method
- finite state
- state space
- dynamic programming
- decision theoretic planning
- transition matrices
- planning under uncertainty
- control problems
- dynamic environments
- reachability analysis
- policy iteration
- model based reinforcement learning
- state and action spaces
- partially observable
- average reward
- markov decision process
- action sets
- average cost
- finite horizon
- reward function
- infinite horizon
- control law
- action space
- factored mdps
- stochastic shortest path
- real time
- decision making