Average-delay optimal policies for the point-to-point channel.
Vineeth Bala SukumaranUtpal MukherjiPublished in: WiOpt (2009)
Keyphrases
- production system
- optimal policy
- multistage
- average cost
- markov decision processes
- reinforcement learning
- dynamic programming
- finite horizon
- decision problems
- state space
- long run
- finite state
- infinite horizon
- state dependent
- sufficient conditions
- dynamic programming algorithms
- single stage
- average reward
- initial state
- serial inventory systems
- bayesian reinforcement learning
- control policies
- markov decision process
- partially observable markov decision processes
- policy iteration
- linear programming
- discounted reward
- inventory models
- finite number
- optimal control
- average reward reinforcement learning
- standard deviation