Enum RLAutoMLAgentType

Namespace

AiDotNet.Enums

Assembly

AiDotNet.dll

Defines which reinforcement learning agent families can be explored by AutoML.

public enum RLAutoMLAgentType

Fields

A2C = 2

Advantage Actor-Critic (A2C) for discrete or continuous control.

DDPG = 3

Deep Deterministic Policy Gradient (DDPG) for continuous control.

DQN = 0

Deep Q-Network (DQN) for discrete action spaces.

PPO = 1

Proximal Policy Optimization (PPO) for discrete or continuous control.

SAC = 4

Soft Actor-Critic (SAC) for continuous control.

Remarks

This enum is used by facade configuration options to select which RL agent types AutoML is allowed to try.

For Beginners: Different RL agents are better suited for different problems:

• DQN is popular for discrete action spaces (like left/right).
• PPO is a strong general-purpose agent (discrete or continuous).
• A2C is a simple actor-critic baseline.
• DDPG and SAC are commonly used for continuous control.