unreal.PositionArraySimilarityReward
¶
- class unreal.PositionArraySimilarityReward(outer: Object | None = None, name: Name | str = 'None')¶
Bases:
LearningAgentsReward
A reward for minimizing the distances of positions in the given arrays.
C++ Source:
Plugin: LearningAgents
Module: LearningAgentsTraining
File: LearningAgentsRewards.h
Editor Properties: (see get_editor_property/set_editor_property)
agent_trainer
(LearningAgentsTrainer): [Read-Only] Reference to the Trainer this reward is associated with.
- classmethod add_position_array_similarity_reward(agent_trainer, name='None', position_num=0, scale=100.000000, weight=1.000000) PositionArraySimilarityReward ¶
Adds a new position array similarity reward to the given trainer. Call during ULearningAgentsTrainer::SetupRewards event.
- Parameters:
agent_trainer (LearningAgentsTrainer) – The trainer to add this reward to.
name (Name) – The name of this new reward. Used for debugging.
position_num (int32) – The number of positions in the array.
scale (float) – Used to normalize the data for the reward.
weight (float) – Multiplier for this reward when being summed up for the total reward.
- Returns:
The newly created reward.
- Return type:
- set_position_array_similarity_reward(agent_id=-1, positions0, positions1, relative_position0=[0.000000, 0.000000, 0.000000], relative_position1=[0.000000, 0.000000, 0.000000], relative_rotation0=[0.000000, 0.000000, 0.000000], relative_rotation1=[0.000000, 0.000000, 0.000000]) None ¶
Sets the data for this reward. Call during ULearningAgentsTrainer::SetRewards event.
- Parameters:
agent_id (int32) – The agent id this data corresponds to.
relative_position0 (Vector) – The vector Positions0 will be offset from.
relative_position1 (Vector) – The vector Positions1 will be offset from.
relative_rotation0 (Rotator) – The frame of reference rotation for Positions0.
relative_rotation1 (Rotator) – The frame of reference rotation for Positions1.