태그
reinforcement learning
ML
Cliff Problem
BartoSutton
Richard S. Sutton
Ricahrd S. Sutton
ubuntu 22.10
Zero-shot Transfer
Batch Gradient Descent
pretrained model
Attention is all you need
dataloader
BGD
Sarsa
Q-Learning
cuDNN
imagenet
resnet
DataStructure
Monte Carlo
nvidia driver
transformer
Batch
CUDA
Coca
rl
Encoder
GD
Dynamic Programming
introduction