Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:algorithm
|
| gptkbp:citation |
high (hundreds)
|
| gptkbp:field |
gptkb:reinforcement_learning
imitation learning |
| gptkbp:fullName |
Aggregate Values to Imitate
|
| https://www.w3.org/2000/01/rdf-schema#label |
AggreVaTe
|
| gptkbp:input |
expert demonstrations
|
| gptkbp:introduced |
gptkb:John_Langford
gptkb:Robert_E._Schapire gptkb:A._Krishnamurthy Alekh Agarwal Nan Jiang |
| gptkbp:introducedIn |
2015
|
| gptkbp:openSource |
gptkb:GitHub
|
| gptkbp:output |
gptkb:public_policy
|
| gptkbp:publishedIn |
Advances in Neural Information Processing Systems (NeurIPS) 2015
|
| gptkbp:purpose |
improve imitation learning by aggregating cost-to-go information
|
| gptkbp:relatedTo |
gptkb:DAgger
imitation learning policy optimization |
| gptkbp:bfsParent |
gptkb:DAgger
|
| gptkbp:bfsLayer |
8
|