From Dissipativity Theory to Compositional Construction of Finite Markov Decision Processes.
Abolfazl LavaeiSadegh SoudjaniMajid ZamaniPublished in: HSCC (2018)
Keyphrases
- markov decision processes
- state and action spaces
- optimal policy
- policy iteration
- finite state
- transition matrices
- state space
- reinforcement learning
- dynamic programming
- decision theoretic planning
- decision processes
- planning under uncertainty
- partially observable
- finite horizon
- model based reinforcement learning
- infinite horizon
- reinforcement learning algorithms
- average reward
- stationary policies
- risk sensitive
- action sets
- reachability analysis
- markov decision process
- decision making
- search space
- monte carlo
- factored mdps
- state abstraction
- reward function
- linear programming
- decision problems