Table 3 Structural comparison of related algorithms.

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

Algorithms

Actors

Critics

Value Correction

Regularization

Cross Policy Update

DDPG

one

one

\(\times\)

\(\times\)

\(\times\)

TD3

one

double

\(\checkmark\)

\(\times\)

\(\times\)

DARC

double

double

\(\checkmark\)

\(\checkmark\)

\(\times\)

M2ACD

double

double

\(\checkmark\)

\(\times\)

\(\checkmark\)