Statements (27)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:Imitation_Learning_Method
|
| gptkbp:alternativeTo |
gptkb:Reinforcement_Learning
|
| gptkbp:application |
gptkb:Video_Game_AI
gptkb:Self-Driving_Cars Drone Flight |
| gptkbp:category |
gptkb:Learning_from_Demonstration
|
| gptkbp:field |
gptkb:Machine_Learning
gptkb:artificial_intelligence gptkb:robot |
| gptkbp:firstDescribed |
1990s
|
| gptkbp:goal |
Mimic Expert Behavior
|
| gptkbp:input |
State-Action Pairs
|
| gptkbp:learnsFrom |
Expert Demonstrations
|
| gptkbp:limitation |
Covariate Shift
Compounding Errors |
| gptkbp:method |
Supervised Learning
|
| gptkbp:notablePublication |
gptkb:Pomerleau,_D.A._(1989)._ALVINN:_An_Autonomous_Land_Vehicle_in_a_Neural_Network.
|
| gptkbp:output |
gptkb:public_policy
|
| gptkbp:relatedTo |
gptkb:Inverse_Reinforcement_Learning
gptkb:Imitation_Learning |
| gptkbp:trainer |
Labeled Demonstrations
|
| gptkbp:usedIn |
gptkb:Robotic_Manipulation
Autonomous Driving Game Playing |
| gptkbp:bfsParent |
gptkb:Imitation_Learning
|
| gptkbp:bfsLayer |
7
|
| http://www.w3.org/2000/01/rdf-schema#label |
Behavioral Cloning
|