Optimal Policy Synthesis from A Sequence of Goal Sets with An Application to Electric Distribution System Restoration.
Ilker IsikOnur Yigit ArpaliEbru Aydin GolPublished in: ADHS (2021)
Keyphrases
- optimal policy
- decision problems
- finite horizon
- markov decision processes
- reinforcement learning
- state space
- infinite horizon
- dynamic programming
- multistage
- long run
- state dependent
- serial inventory systems
- control policies
- markov decision process
- initial state
- average cost
- average reward
- bayesian reinforcement learning
- probability distribution
- partially observable markov decision processes
- random variables
- stochastic demand
- demand distributions
- partially observable
- sufficient conditions
- markov decision problems