Class ABlueprintTrainer
- class ABlueprintTrainer : public AAbstractTrainer
-
A blueprint subclass of AAbstractTrainer that implements the abstract methods.
Note
This class is designed to be subclassed in Blueprint to implement the specific training logic for an NPC.
Public Functions
- virtual float ComputeReward() override
-
Collect a reward from the agent’s immediate environment.
Implemented by a blueprint subclass
- Returns:
-
float representing the agents reward
- virtual EAgentTrainingStatus ComputeStatus() override
-
Check if agent is in a terminal state.
Implemented by a blueprint subclass
- Returns:
-
The status of the agent which informs whether it is still running, or why it stopped.