Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:algorithm
|
| gptkbp:application |
robotics
game playing autonomous driving |
| gptkbp:approach |
adversarial training
|
| gptkbp:arXivID |
1710.11248
|
| gptkbp:field |
gptkb:machine_learning
gptkb:reinforcement_learning |
| gptkbp:fullName |
Adversarial Inverse Reinforcement Learning
|
| gptkbp:goal |
recover reward functions from expert demonstrations
|
| https://www.w3.org/2000/01/rdf-schema#label |
AIRL
|
| gptkbp:introducedIn |
2017
|
| gptkbp:notablePublication |
Adversarial Inverse Reinforcement Learning (Fu et al., 2017)
|
| gptkbp:proposedBy |
gptkb:Matthew_Botvinick
gptkb:Sergey_Levine gptkb:Trevor_Darrell Justin Fu Krzysztof Choromanski |
| gptkbp:relatedTo |
gptkb:Inverse_Reinforcement_Learning
gptkb:Imitation_Learning Generative Adversarial Imitation Learning |
| gptkbp:uses |
policy network
discriminator network |
| gptkbp:bfsParent |
gptkb:Airoli_Railway_Station
|
| gptkbp:bfsLayer |
6
|