Path-Integral-Based Reinforcement Learning Algorithm for Goal-Directed Locomotion of Snake-Shaped Robot

Table 3

The shape parameters of each obstacle.

Obstacle	Shape							Center of the obstacle
1	Sphere	5	5	5	1	1	1	(20, 20, 0)
2	Sphere	7	7	7	1	1	1	(30,−2,0)
3	Cone	6	6	9	1	1	0.3	(33, 27, 0)
4	Cone	12	12	19	1	1	0.3	(3, 27, 0)
5	Cone	12	12	21	1	1	0.3	(6, 3, 0)
6	Cone	6	6	21	1	1	0.3	(30, 36, 0)