Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:author |
Continuous control with deep reinforcement learning
Random synaptic feedback weights support error backpropagation for deep learning |
| gptkbp:doctoralAdvisor |
Peter E. Latham
|
| gptkbp:education |
gptkb:Queen's_University
gptkb:University_of_Oxford |
| gptkbp:employer |
gptkb:DeepMind
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning computational neuroscience |
| gptkbp:hasORCID |
0000-0002-2377-5352
|
| gptkbp:hasWorkedWith |
gptkb:DeepMind
|
| https://www.w3.org/2000/01/rdf-schema#label |
Timothy P. Lillicrap
|
| gptkbp:nationality |
gptkb:Canadian
|
| gptkbp:notableWork |
work on deep reinforcement learning
work on neural network learning algorithms |
| gptkbp:occupation |
gptkb:computer_scientist
gptkb:neuroscientist |
| gptkbp:bfsParent |
gptkb:DDPG
|
| gptkbp:bfsLayer |
7
|