New answers tagged hyper-parameters
2
votes
Accepted
Which paper describes the effect of learning_starts in Reinforcement Learning?
The replay buffer allows breaking the temporal dependence of the data and thus makes them more i.i.d. (which is what we want). The replay buffer needs to be at least filled with enough experience to ...
Top 50 recent answers are included
Related Tags
hyper-parameters × 85hyperparameter-optimization × 33
neural-networks × 24
deep-learning × 19
reinforcement-learning × 17
machine-learning × 12
deep-rl × 10
convolutional-neural-networks × 9
activation-functions × 6
filters × 6
training × 5
dqn × 3
long-short-term-memory × 3
autoencoders × 3
variational-autoencoder × 3
neuroevolution × 3
regularization × 3
artificial-neuron × 3
hidden-layers × 3
learning-rate × 3
batch-size × 3
comparison × 2
q-learning × 2
recurrent-neural-networks × 2
ai-design × 2