Decomposable Markov Decision Processes: A Fluid Optimization Approach.
Dimitris BertsimasVelibor V. MisicPublished in: Oper. Res. (2016)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- policy iteration
- reinforcement learning
- transition matrices
- dynamic programming
- planning under uncertainty
- reinforcement learning algorithms
- finite horizon
- average cost
- markov decision process
- infinite horizon
- decision processes
- average reward
- factored mdps
- reachability analysis
- model based reinforcement learning
- action space
- risk sensitive
- decision theoretic planning
- data mining
- function approximation
- semi markov decision processes
- state and action spaces
- action sets