Figure22
Figure 22. Convergences of improved DDPG and CPER-MADDPG algorithms. DDPG: Deep deterministic policy gradient; CPER-MADDPG: combined prioritized experience replay with multi-intelligent depth deterministic policy gradient.
Intelligence & Robotics
ISSN 2770-3541 (Online)
Navigation
Navigation
Committee on Publication Ethics
https://publicationethics.org/members/intelligence-robotics
Portico
All published articles are preserved here permanently:
https://www.portico.org/publishers/oae/
