Research Beginner

Inverse RL Apprenticeship Learning Activation function Linear Programming Inverse Reinforcement Learning Lambda-Return n-Step Return Regularization Artificial Intelligence Reinforcement Learning SVM irl Machine Learning Optimization Ai 무조코 설치 mujoco-py ~/.mujoco mjkey.txt getid_osx Mujoco maximum causal entropy IRL GAIL Maximum Entropy IRL Principle of Maximum Entropy The Principle of Maximum Causal Entropy Soft margin SVM subgradient method Quadratic Program Maximum Margin Maximum Margin Planning inverse image invertible one-to-one Codomain dunumerable Set theory Feature expectations Quadratic Programming Model Ensemble Data Preprocessing Exploration Process Optimization Criterion Safe RL Safe Reinforcement Learning Max Pooling zero pad activation map Convolution Layer Fully Connected Layer Computational graph Imitation Learning reward function Analytic gradient Numerical gradient Multinomial Logistic Regression L2 regularization L1 regularization Linear Classifier Hyperparameters 무기생산 기초의 중요성 해야하는 것 환경의 중요성 Monte-Carlo Prediction Method 일단한다 생각담기 GAE code Trust Region Optimization Reward Shaping gamma-just estimator TRPO High-Dimensional Generalized Advantage Estimation TD(lambda) TD(0) Deep Reinforcement Learning I2A Imagination-Augmented Agents Convolutional Neural Network Convolutional Atari Game Deep Q-Network Q-learning Actor-Critic Policy Gradient anticipatory meta-action A3C Anticipatory Asynchronous Advantage Actor-Critic Transfer Learning Hyperparameter Optimization Weight Initialization pooling layer Softmax classifier Linear classification Loss function cs231n Data Augmentation Dropout Batch Normalization eligibility trace Temporal-Difference Monte-Carlo 잘하는 일 backward Convolutional Neural Networks image classification Stochastic gradient descent L1 Distance L2 Distance Gradient Descent backpropagation A4C deep learning maximum entropy countable stride chain rule 하고싶은 것 anticipation MDP entropy Ms. SGD ppo Cardinality Uncountable QP neural network sarsa 좋아하는 일 neuron DQN onto td Ph.D gae node padding rollout gan planning filter forward research math Setup simulation LAYER 존중 대학원 imagination 수식 Gate environment study 존경 channel 박사 cnn 스터디 연사 발표 환경 LP MC 프로젝트 수영 비교 just do it domain 수학 MATHEMATICS 취업