Representation Enhancement-Based Proximal Policy Optimization for UAV Path Planning and Obstacle Avoidance

Table 5

Success rate statistics in Scenario B.

Training step	ASN	AS	AN	SN
50K	25%	13%	6%	1%
100K	39%	19%	11%	2%
150K	56%	24%	16%	2%
200K	66%	29%	19%	3%
250K	72%	33%	23%	2%
300K	79%	39%	26%	2%