Mobile Edge Offloading Using Markov Decision Processes.
Khalid R. AlasmariRobert C. Green IIMansoor AlamPublished in: EDGE (2018)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- reinforcement learning
- transition matrices
- dynamic programming
- decision theoretic planning
- planning under uncertainty
- reinforcement learning algorithms
- average cost
- policy iteration
- finite horizon
- factored mdps
- reachability analysis
- partially observable
- action space
- infinite horizon
- model based reinforcement learning
- markov decision process
- decision processes
- action sets
- probabilistic planning
- reward function
- multistage
- discounted reward
- risk sensitive
- average reward