On Optimal Policies for Network-Coded Cooperation: Theory and Implementation.
Hana KhamfroushDaniel E. LucaniPeyman PahlevaniJoão BarrosPublished in: IEEE J. Sel. Areas Commun. (2015)
Keyphrases
- optimal policy
- reinforcement learning
- markov decision processes
- finite state
- state space
- decision problems
- dynamic programming algorithms
- dynamic programming
- long run
- finite horizon
- multistage
- infinite horizon
- average cost
- np hard
- average reward
- multi agent
- serial inventory systems
- data mining
- partially observable
- markov decision process
- control policies
- bayesian reinforcement learning