From Dissipativity Theory to Compositional Construction of Finite Markov Decision Processes.
Abolfazl LavaeiSadegh Esmaeil Zadeh SoudjaniMajid ZamaniPublished in: CoRR (2017)
Keyphrases
- markov decision processes
- state and action spaces
- state space
- reinforcement learning
- transition matrices
- optimal policy
- finite state
- policy iteration
- decision theoretic planning
- reachability analysis
- dynamic programming
- reinforcement learning algorithms
- finite horizon
- infinite horizon
- decision processes
- partially observable
- average cost
- factored mdps
- planning under uncertainty
- average reward
- action space
- model based reinforcement learning
- partially observable markov decision processes
- action sets
- markov decision process
- reward function
- supply chain
- stationary policies
- risk sensitive
- data mining
- function approximation
- search space
- semi markov decision processes
- learning algorithm
- machine learning