Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:canBe |
gptkb:convolutional_neural_network
gptkb:Recurrent_Neural_Network Feedforward Neural Network Deterministic Stochastic |
| gptkbp:function |
Approximates Policy Function
|
| https://www.w3.org/2000/01/rdf-schema#label |
Policy Network
|
| gptkbp:input |
gptkb:state_order
|
| gptkbp:learns |
gptkb:public_policy
|
| gptkbp:output |
gptkb:action
|
| gptkbp:relatedTo |
Value Network
|
| gptkbp:trainer |
Reinforcement Learning Algorithms
|
| gptkbp:usedIn |
gptkb:Trust_Region_Policy_Optimization
gptkb:Reinforcement_Learning gptkb:Proximal_Policy_Optimization Actor-Critic Methods Deep Reinforcement Learning Policy Gradient Methods Deterministic Policy Gradient Stochastic Policy Gradient |
| gptkbp:bfsParent |
gptkb:Roger_Liddle
|
| gptkbp:bfsLayer |
7
|