End-to-End Autonomous Exploration with Deep Reinforcement Learning and Intrinsic Motivation

Table 1

Experiment results of sample separation parameter.

	TC-network (%)	POSM (%)
1	88.68	31.25
2	91.53	22.34
3	93.06	16.27
4	92.32	12.51
5	90.87	11.63
7	86.59	12.48
10	81.93	12.65