Optimal Policies for a Pandemic: A Stochastic Game Approach and a Deep Learning Algorithm.

Yao Xuan Robert Balkin Jiequn Han Ruimeng Hu Héctor D. Ceniceros

Published in: CoRR (2020)

Keyphrases

optimal policy
learning algorithm
reinforcement learning
control policies
state dependent
markov decision processes
decision problems
stochastic inventory control
state space
finite horizon

infinite horizon
dynamic programming
long run
multistage
reinforcement learning algorithms
finite state
dynamic programming algorithms
sufficient conditions
average reward
monte carlo

game playing
average cost
long run average cost
optimal strategy
average reward reinforcement learning
base stock policies
monte carlo tree search
machine learning
markov decision process
semi markov decision processes

periodic review
serial inventory systems
lost sales
initial state
sample path
markov decision problems
learning agent
policy iteration
multi agent