Reinforcement Learning for Optimization of COVID-19 Mitigation policies.
Varun KompellaRoberto CapobiancoStacy JongJonathan BrowneSpencer J. FoxLauren Ancel MeyersPeter R. WurmanPeter StonePublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- global optimization
- function approximation
- optimization problems
- markov decision processes
- optimization algorithm
- decision problems
- reward function
- constrained optimization
- robotic control
- multi agent reinforcement learning
- reinforcement learning algorithms
- model free
- optimization methods
- state space
- dynamic programming
- risk management
- control policy
- continuous state
- reinforcement learning agents
- multi agent