|
gptkb:Q-learning_algorithm
|
Q-values
|
|
gptkb:Recurrent_neural_network_based_language_model
|
probability distribution over sequences of words
|
|
gptkb:Generative_Models
|
gptkb:Probability_Distribution
|
|
gptkb:Markov_Logic_Network
|
weights of logic formulas
|
|
gptkb:Knowledge_Graph_Convolutional_Network
|
entity representations
|
|
gptkb:TD(0)
|
state value function
|
|
gptkb:Variational_autoencoder
|
latent variable model
|
|
gptkb:Model-Free_Learning
|
Policies
|
|
gptkb:Linear_Classifier
|
Weights
|
|
gptkb:Model-Free_Learning
|
Value Functions
|
|
gptkb:Policy_Network
|
gptkb:public_policy
|
|
gptkb:Linear_Classifier
|
Bias
|
|
gptkb:Maximum_Entropy_Markov_Model
|
conditional probability distribution
|
|
gptkb:Sequence_Models
|
Temporal dependencies
|
|
gptkb:Sigurd_the_Dragon_Slayer
|
language of birds
|
|
gptkb:Knowledge_Graph_Convolutional_Network
|
relation representations
|
|
gptkb:Policy_Gradient
|
Parameterization of Policy
|
|
gptkb:Adaptive_Neuro-Fuzzy_Inference_System
|
membership function parameters
|
|
gptkb:Hierarchical_Bayesian_Optimization_Algorithm
|
problem structure
|
|
gptkb:Layer_2_switches
|
MAC addresses dynamically
|