On the Existence of Optimal Policies for a Class of Static and Sequential Dynamic Teams.
Abhishek GuptaSerdar YükselTamer BasarCedric LangbortPublished in: CoRR (2014)
Keyphrases
- optimal policy
- markov decision processes
- dynamic programming
- decision problems
- finite state
- infinite horizon
- reinforcement learning
- finite horizon
- state space
- average reward reinforcement learning
- serial inventory systems
- bayesian reinforcement learning
- dynamic programming algorithms
- long run
- multistage
- state dependent
- average reward
- average cost
- finite number
- objective function