Refined Path Planning for Emergency Rescue Vehicles on Congested Urban Arterial Roads via Reinforcement Learning Approach

Figure 6

Average reward of PERDQN and DQN among training steps under different schemes in case 2. (a) Average reward under scheme 1. (b) Average reward under scheme 2. (c) Average reward under scheme 3. (d) Average reward under scheme 4. (e) Average reward comparison of PERDQN among four schemes.

(a)

(b)

(c)

(d)

(e)