Learn the optimal public policy to end the epidemic using Reinforcement Learning.
Current Public Policies :
- Vaccination Block Policy
- Quarantine Block Policy
The RL Agent uses variants of the Deep Q Learning Networks (DQN).
Current variants are :
- Linear DQN (The only network without convolutional networks)
- DQN (with and without target networks)
- Double DQN
- Dueling DQN
- Dueling Double DQN