Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:award |
gptkb:IEEE_Fellow
gptkb:AAAI_Fellow |
| gptkbp:doctoralAdvisor |
gptkb:Thomas_G._Dietterich
|
| gptkbp:education |
gptkb:Rutgers_University
gptkb:Indian_Institute_of_Technology_Madras |
| gptkbp:employer |
gptkb:University_of_Massachusetts_Amherst
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning gptkb:reinforcement_learning representation learning |
| https://www.w3.org/2000/01/rdf-schema#label |
Sridhar Mahadevan
|
| gptkbp:nationality |
gptkb:Indian
|
| gptkbp:notableWork |
graph-based learning methods
proto-value functions representation discovery in reinforcement learning |
| gptkbp:occupation |
gptkb:computer_scientist
|
| gptkbp:position |
gptkb:professor
|
| gptkbp:bfsParent |
gptkb:Michael_I._Jordan
|
| gptkbp:bfsLayer |
6
|