• ML
  • 머리말
  • 학습준비: 환경 구축
  • 시작하기
    • "hello tensorflow" 예제
  • 머신러닝 분류
  • 알고리즘
    • 선형회귀분석(renear regression)
    • 로지스틱 회귀 (logistic regression:classification)
    • 단일 계층 신경망: MNIST
    • 군집화 (clustering)
    • word2vec
    • CNN (Convolutional Neural Network) (To-be)
    • RNN (Recurrent Neural Network) (To-be)
    • RL (Reinforcement Learning)
      • Lecture 2: OpenAI GYM 게임해보기
      • Lecture 3: Dummy Q-learning (table)
      • Lecture 4: Q-learning (table)
      • Lecture 5: Q-learning in non-deterministic world
      • Lecture 6-1: Q Network for Frozen Lake
      • Lecture 6-2: Q Network for Cart Pole
  • 함수 정리
  • 용어집
Powered by GitBook

RL (Reinforcement Learning)

모두를 위한 머신러닝/딥러닝 강의 코드

RL (Reinforcement Learning)

실습 과정 중 동작을 위해 극히 일부 코드 수정. (python3.5)

  • Lecture 2: OpenAI GYM 게임해보기
  • Lecture 3: Dummy Q-learning (table)
  • Lecture 4: Q-learning (table)
  • Lecture 5: Q-learning in non-deterministic world
  • Lecture 6-1: Q Network for Frozen Lake
  • Lecture 6-2: Q Network for Cart Pole

또 다른 gym의 실습 결과

  • gym-test

results matching ""

    No results matching ""