Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:architecture |
gptkb:deep_Q-network
|
| gptkbp:citation |
over 200 (as of 2024)
|
| gptkbp:fullName |
gptkb:Deep_Reinforcement_Relevance_Network
|
| https://www.w3.org/2000/01/rdf-schema#label |
DRRN
|
| gptkbp:input |
action text
state text |
| gptkbp:introduced |
gptkb:Jianfeng_Gao
gptkb:Xiaodong_He gptkb:James_M._Turner He He |
| gptkbp:introducedIn |
2016
|
| gptkbp:notableFor |
separately encoding state and action representations
applying Q-learning to text-based environments |
| gptkbp:notablePublication |
gptkb:Deep_Reinforcement_Learning_with_a_Natural_Language_Action_Space
https://arxiv.org/abs/1511.07275 |
| gptkbp:output |
Q-value
|
| gptkbp:usedFor |
deep reinforcement learning
text-based games natural language action spaces |
| gptkbp:bfsParent |
gptkb:Diori_Hamani_International_Airport
|
| gptkbp:bfsLayer |
6
|