14. DDPG: Deep Deterministic Policy Gradient, Continuous Actions
DDPG: Deep Deterministic Policy Gradient, Continuous Action-space
M3 L5 14 DDPG Deep Deterministic Policy Gradient Continuous Actionspace V1
In the DDPG paper, they introduced this algorithm as an "Actor-Critic" method. Though, some researchers think DDPG is best classified as a DQN method for continuous action spaces (along with NAF). Regardless, DDPG is a very successful method and it's good for you to gain some intuition.