Multiagent Cooperative Learning Strategies for Pursuit-Evasion Games

Table 1

Average number of capture steps in different environments.

	Grid size	Without obstacles; (steps)	With obstacles; (steps)
Hysteretic Q-Learning	12 * 12	68	73
RL-Fusing	12 * 12	61	65
The proposed approach	12 * 12	24	27