Table 4 Correlation algorithm comparison.

From: Deep reinforcement learning trajectory planning for robotic manipulator based on simulation-efficient training

Algorithms

Time (s/episode)

Mutation of success rate

DDPG

1.26

\(\checkmark\)

TD3

1.24

\(\checkmark\)

M2ACD without TSR

1.19

\(\times\)

M2ACD

0.98

\(\times\)

Back to article page