unreal.LearningAgentsPolicySettings

class unreal.LearningAgentsPolicySettings

Bases: StructBase

The configurable settings for a ULearningAgentsPolicy.

C++ Source:

• Plugin: LearningAgents

• Module: LearningAgents

• File: LearningAgentsPolicy.h

Editor Properties: (see get_editor_property/set_editor_property)

• action_noise_max (float): [Read-Write] Maximum action noise used by the policy

• action_noise_min (float): [Read-Write] Minimum action noise used by the policy

• action_noise_scale (float): [Read-Write] Scale of the action noise used by the policy should be 1.0 during training.

• action_noise_seed (int32): [Read-Write] Seed for the action noise used by the policy

• activation_function (LearningAgentsActivationFunction): [Read-Write] Activation function to use on hidden layers of the policy network

• hidden_layer_size (int32): [Read-Write] Number of neurons in each hidden layer of the policy network

• layer_num (int32): [Read-Write] Total layers for policy network including input, hidden, and output layers