Multilayer Deep Deterministic Policy Gradient for Static Safety and Stability Analysis of Novel Power Systems

Table 1

The classification of deep reinforcement learning methods.

Type	Action space	Methods
Value-based	Discrete	Q learning, DQN, state-action-reward-state-action
Policy-based	Discrete or continuous	Policy gradient
Actor-critic	Discrete or continuous	Actor-critic, PPO, trust region policy optimization
Actor-critic	Continuous	DDPG, twin-delayed DDPG, soft actor-critic