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)
activation_function
(LearningAgentsActivationFunction): [Read-Write] Activation function to use on hidden layers of the policy networkhidden_layer_num
(int32): [Read-Write] Number of hidden layers for policy network.hidden_layer_size
(int32): [Read-Write] Number of neurons in each hidden layer of the policy networkinitial_encoded_action_scale
(float): [Read-Write] Initial scale for encoded actions. Setting this <1 reduces the initial bias from the network random weights and tends to help training.memory_state_size
(int32): [Read-Write] Number of neurons in the memory state of the policy networkuse_memory
(bool): [Read-Write] If this network should use memory or not. Setting this to false is equivalent to setting MemoryStateSize to 0.