Optimal Policy Learning for Disease Prevention Using Reinforcement Learning

Table 1

The comparison of three reinforcement learning algorithms explained in the paper in terms of best rewards and best policy when the agent is executed for 100 episodes.

Algorithm	Best reward	Optimal policy
		Year 1	Year 2	Year 3	Year 4	Year 5
Random	174.16	[0.2, 0.7]	[0.6, 0.9]	[0.1, 0.8]	[0.4, 0.6]	[0.3, 0.1]
Q-Learning	228.77	[0.3, 0.1]	[0.3, 0.2]	[0.5, 0.2]	[0.9, 0.5]	[0.5, 0.1]
SARSA	161.74	[0.3, 0.1]	[0.3, 0.1]	[0.3, 0.1]	[0.3, 0.1]	[0.3, 0.1]
DDPG	325.55	[1.0, 0.8]	[0.1, 0.0]	[0.1, 0.8]	[0.6, 1.0]	[0.6, 1.0]