Inverse Reinforcement Learning
GPTKB entity
Statements (29)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
machine learning method
|
| gptkbp:application |
robotics
autonomous driving imitation learning human behavior modeling |
| gptkbp:challenge |
computational complexity
partial observability ambiguity in reward inference |
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning |
| gptkbp:goal |
infer reward function from observed behavior
|
| https://www.w3.org/2000/01/rdf-schema#label |
Inverse Reinforcement Learning
|
| gptkbp:introduced |
gptkb:Andrew_Ng
gptkb:Stuart_Russell |
| gptkbp:introducedIn |
2000
|
| gptkbp:key |
gptkb:Algorithms_for_Inverse_Reinforcement_Learning_(Ng_&_Russell,_2000)
|
| gptkbp:method |
gptkb:Bayesian_IRL
gptkb:maximum_entropy_IRL feature matching |
| gptkbp:relatedConcept |
apprenticeship learning
behavioral cloning reward engineering |
| gptkbp:relatedTo |
gptkb:Reinforcement_Learning
|
| gptkbp:usedIn |
multi-agent systems
AI safety preference learning |
| gptkbp:bfsParent |
gptkb:AIRL
gptkb:Imitation_Learning |
| gptkbp:bfsLayer |
7
|