SIR-RL: Reinforcement Learning for Optimized Policy Control during Epidemiological Outbreaks in Emerging Market and Developing Economies.
Maeghal JainZiya UddinWubshet IbrahimPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- control policy
- optimal policy
- action selection
- control policies
- control problems
- rl algorithms
- optimal control
- public health
- function approximation
- approximate dynamic programming
- actor critic
- markov decision process
- policy search
- state space
- reinforcement learning algorithms
- control strategies
- action space
- markov decision processes
- policy gradient
- policy iteration
- model free
- state and action spaces
- adaptive control
- reinforcement learning problems
- reward function
- policy evaluation
- control system
- function approximators
- long run
- state action
- learning algorithm
- partially observable
- temporal difference
- dynamic programming
- partially observable domains
- machine learning
- approximate policy iteration
- markov decision problems
- transfer learning
- partially observable environments
- continuous state
- learning process
- multi agent
- total reward
- reward signal
- reinforcement learning methods
- temporal difference learning
- learning agent
- partially observable markov decision processes
- robot control
- infinite horizon
- learning problems