cooperative inverse reinforcement learning
GPTKB entity
Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
machine learning method
|
| gptkbp:application |
human-robot interaction
value alignment |
| gptkbp:approach |
models human-AI cooperation as a game
|
| gptkbp:describedBy |
Hadfield-Menell et al. 2016
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning |
| gptkbp:goal |
align AI objectives with human preferences
|
| https://www.w3.org/2000/01/rdf-schema#label |
cooperative inverse reinforcement learning
|
| gptkbp:method |
infers reward functions from cooperative behavior
|
| gptkbp:proposedBy |
gptkb:Pieter_Abbeel
gptkb:Stuart_Russell gptkb:Anca_Dragan gptkb:Dylan_Hadfield-Menell |
| gptkbp:publishedIn |
Advances in Neural Information Processing Systems (NeurIPS) 2016
|
| gptkbp:relatedTo |
inverse reinforcement learning
cooperative AI |
| gptkbp:url |
https://arxiv.org/abs/1606.03137
|
| gptkbp:yearProposed |
2016
|
| gptkbp:bfsParent |
gptkb:Superintelligent_AI
gptkb:AI_Alignment |
| gptkbp:bfsLayer |
7
|