Assessing the appropriateness of using markov decision processes for RF spectrum management.
John MeierBenjamin KarausSreeharsha SistlaTerry TidwellRoger D. ChamberlainChristopher D. GillPublished in: MSWiM (2013)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- reinforcement learning
- state space
- decision theoretic planning
- transition matrices
- dynamic programming
- finite horizon
- policy iteration
- reachability analysis
- average cost
- average reward
- decision processes
- partially observable
- factored mdps
- markov decision process
- reinforcement learning algorithms
- infinite horizon
- decision making
- planning under uncertainty
- model based reinforcement learning
- risk sensitive
- state and action spaces
- action sets
- action space
- decision problems
- semi markov decision processes
- least squares
- interval estimation
- multi agent
- multi agent systems
- model checking
- state abstraction
- real valued
- reward function