On optimising taboo criteria in Markov decision processes.
Kartikeya S. PuranamMichael N. KatehakisPublished in: Int. J. Appl. Decis. Sci. (2014)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- transition matrices
- dynamic programming
- reinforcement learning
- model based reinforcement learning
- policy iteration
- reachability analysis
- finite horizon
- factored mdps
- infinite horizon
- decision theoretic planning
- average cost
- reinforcement learning algorithms
- planning under uncertainty
- action space
- partially observable
- markov decision process
- average reward
- action sets
- discounted reward
- decision processes
- risk sensitive
- state and action spaces
- reward function
- monte carlo
- interval estimation