Optimal Policies for a Pandemic: A Stochastic Game Approach and a Deep Learning Algorithm.
Yao XuanRobert BalkinJiequn HanRuimeng HuHéctor D. CenicerosPublished 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