Optimal Policy for Task Migration to UAV in Discrete-Time Systems with Firm Deadlines.
Khai DoanWesley AraujoEvangelos KranakisIoannis LambadarisYannis ViniotisPublished in: CoRR (2022)
Keyphrases
- optimal policy
- markov decision processes
- infinite horizon
- finite horizon
- reinforcement learning
- decision problems
- state dependent
- dynamic programming
- state space
- multistage
- inventory level
- long run
- finite state
- develop a mathematical model
- optimal pricing
- control policies
- policy iteration
- markov decision process
- machine learning
- lot sizing
- probability distribution
- learning algorithm