드롭아웃 dropout 선형 회귀 Linear Regression 오토인코더 Weight Regularization 배치 정규화 Hyperbolic Tangent Function 하이퍼볼릭 탄젠트 함수 단어 임베딩 교차 검증 Softmax Regression 소프트맥스 회귀 QAC TD Method MC Method 강화 학습 DDPG DDDQN Dueling DQN Double DQN REINFORCE Function Approximate Model-Free Prediction MC Control Model-Free Control Value Iteration Policy Evaluation Policy Improvement Policy Iteration 합성곱 신경망 순환 신경망 A3C Actor-Critic Policy Gradient OpenAI gym 가중치 규제 Word Embedding Batch Normalization AutoEncoder lstm Q-Learning 경사 하강법 신경망 학습 gradient descent Logistic Regression 로지스틱 회귀 rnn PPO cross validation A2C DQN Bellman Equation perceptron Xavier MDP MRP He CNN Dynamic Programming