Diversity Evolutionary Policy Deep Reinforcement Learning

Table 1

The test environment in the MuJoCo benchmark.

Environment	Action dimension/state dimension	Task goals
Hopper-v2	3/11	Make a two-dimensional one-legged robot hop forward as fast as possible
HalfCheetah-v2	6/17	Make the 2D cheetah robot run fast
Ant-v2	8/111	Make a four-legged creature walk forward as fast as possible
Walker2d-v2	6/17	Make a two-dimensional bipedal robot walk forward as fast as possible