Policy Gradient Methods

Deep Deterministic Policy Gradient

Introduced by Lillicrap et al. in Continuous control with deep reinforcement learning

DDPG, or Deep Deterministic Policy Gradient, is an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. It combines the actor-critic approach with insights from DQNs: in particular, the insights that 1) the network is trained off-policy with samples from a replay buffer to minimize correlations between samples, and 2) the network is trained with a target Q network to give consistent targets during temporal difference backups. DDPG makes use of the same ideas along with batch normalization.

Source: Continuous control with deep reinforcement learning


Paper Code Results Date Stars


Task Papers Share
Continuous Control 28 26.42%
OpenAI Gym 13 12.26%
Management 7 6.60%
Decision Making 5 4.72%
Autonomous Driving 5 4.72%
Imitation Learning 4 3.77%
Multi-agent Reinforcement Learning 3 2.83%
Unity 3 2.83%
energy management 3 2.83%