1. Epic GamesDeveloper
  3. ULearningAgentsTrainingEnvironment

ULearningAgentsTrainingEnvironment

API > API/Plugins > API/Plugins/LearningAgentsTraining

Inheritance Hierarchy

References

   
Module LearningAgentsTraining
Header /Engine/Plugins/Experimental/LearningAgents/Source/LearningAgentsTraining/Public/LearningAgentsTrainingEnvironment.h
Include #include "LearningAgentsTrainingEnvironment.h"

Syntax

UCLASS (Abstract, HideDropDown, BlueprintType, Blueprintable)  
class ULearningAgentsTrainingEnvironment : public ULearningAgentsManagerListener

Constructors

  Type Name Description
Public function   -- Setup --
Public function    

Destructors

  Type Name Description
Public function Virtual    

Functions

  Type Name Description
Public function UFunction Category, Meta blueprintnativeevent void

GatherAgentCompletion ( ELearningAgentsCompletion& OutCompletion,
const int32 AgentId
)

 -- Completions --
Public function UFunction Category, Meta blueprintnativeevent void

GatherAgentCompletions ( TArray< ELearningAgentsCompletion >& OutCompletions,
const TArray< int32 >& AgentIds
)

 This callback can be overridden by the Trainer and gathers all the completions for the given set of agents.
Public function UFunction Category, Meta blueprintnativeevent void

GatherAgentReward ( float& OutReward,
const int32 AgentId
)

 -- Rewards --
Public function UFunction Category, Meta blueprintnativeevent void

GatherAgentRewards ( TArray< float >& OutRewards,
const TArray< int32 >& AgentIds
)

 This callback can be overridden by the Trainer and gathers all the reward values for the given set of agents.
Public function UFunction BlueprintCallable, Category void Call this function when it is time to evaluate the completions for your agents.
Public function UFunction BlueprintCallable, Category void -- Training Process --
Public function Const UE::Learning::ECompletionMode

GetAgentCompletion ( const int32 AgentId
)

 Gets the agent completion mode for the given agent id.
Public function Const const TLearningArrayView< 1, const UE::Learning::ECompletionMode > Gets the agent completions as a const array view.
Public function Const const TLearningArrayView< 1, const UE::Learning::ECompletionMode > Gets the all completions as a const array view.
Public function Const UFunction BlueprintPure, Category, Meta ELearningAgentsCompletion

GetCompletion ( const int32 AgentId
)

 Gets the current completion for an agent. Should be called only after GatherCompletions.
Public function Const uint64

GetCompletionIteration ( const int32 AgentId
)

 Gets the completion iteration value for the given agent id.
Public function TLearningArrayView< 1, UE::Learning::ECompletionMode > Gets the episode completions as a mutable array view.
Public function Const UFunction BlueprintPure, Category, Meta float

GetEpisodeTime ( const int32 AgentId
)

 Gets the current elapsed episode time for the given agent.
Public function Const UE::Learning::FResetInstanceBuffer &  
Public function Const UFunction BlueprintPure, Category, Meta float

GetReward ( const int32 AgentId
)

 Gets the current reward for an agent. Should be called only after GatherRewards.
Public function Const const TLearningArrayView< 1, const float > -- Non-blueprint public interface --
Public function Const uint64

GetRewardIteration ( const int32 AgentId
)

 Gets the reward iteration value for the given agent id.
Public function Const UFunction BlueprintPure, Category, Meta bool

HasCompletion ( const int32 AgentId
)

 Returns true if GatherCompletions has been called and the completion already set for the given agent.
Public function Const UFunction BlueprintPure, Category, Meta bool

HasReward ( const int32 AgentId
)

 Returns true if GatherRewards has been called and the reward already set for the given agent.
Public function Static UFunction BlueprintCallable, Category, Meta ULearningAgentsTrainingEnvironment * Constructs the training environment and runs the setup functions for rewards and completions.
Public function Virtual void

OnAgentsAdded_Implementation ( const TArray< int32 >& AgentIds
)

  
Public function Virtual void

OnAgentsManagerTick_Implementation ( const TArray< int32 >& AgentIds,
const float DeltaTime
)

  
Public function Virtual void  
Public function Virtual void

OnAgentsReset_Implementation ( const TArray< int32 >& AgentIds
)

  
Public function UFunction Category, Meta blueprintnativeevent void

ResetAgentEpisode ( const int32 AgentId
)

 -- Resets --
Public function UFunction Category, Meta blueprintnativeevent void

ResetAgentEpisodes ( const TArray< int32 >& AgentIds
)

 This callback can be overridden by the Trainer and resets all episodes for each agent in the given set.
Public function void Computes a combined completion buffer for agents that have been completed manually and those which have reached the maximum episode length.
Public function UFunction BlueprintCallable, Category, Meta void Initializes the training environment and runs the setup functions for rewards and completions.

Ask questions and help your peers Developer Forums

Write your own tutorials or read those from others Learning Library

On this page