Computationally efficient algorithms for on-line optimization of markov decision processes.
A. JalaliMichael J. FergusonPublished in: Autom. (1992)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- policy iteration
- reinforcement learning
- dynamic programming
- transition matrices
- reinforcement learning algorithms
- reachability analysis
- model based reinforcement learning
- average reward
- partially observable
- decision processes
- factored mdps
- markov decision process
- finite horizon
- planning under uncertainty
- decision theoretic planning
- action space
- infinite horizon
- semi markov decision processes
- risk sensitive
- decision problems
- markov decision problems
- monte carlo
- action sets
- reward function
- control strategy
- multi agent