본문 바로가기
Research/Machine Learning

강화학습, Exponentially weighted average계산하기

by 곽동현 IMCOMKING 2019. 1. 22.

https://gist.github.com/imcomking/b1acbb891ac4baa69f32d9eb4c221fb9


def exponentially_weighted_matrix(discount, mat_len):
DisMat = np.triu(np.ones((mat_len, mat_len)) * discount, k=1)
DisMat[DisMat==0] = 1
DisMat = np.cumprod(DisMat, axis=1)
DisMat = np.triu(DisMat)
return DisMat

def exponentially_weighted_cumsum(discount, np_data):
DisMat = exponentially_weighted_matrix(discount, np_data.shape[0])
value = np.dot(DisMat, np_data.reshape(-1, 1))
return value[::-1].transpose()[0]



'Research > Machine Learning' 카테고리의 다른 글

소리 합성  (0) 2019.12.09
물리학에 기반한 모델  (0) 2019.05.15
강화학습, Exponentially weighted average계산하기  (0) 2019.01.22
PID 제어  (0) 2018.11.13
Belief Propagation  (0) 2018.01.05
Thompson Sampling, Multi-armed bandit, Contextual bandit  (0) 2018.01.05

댓글0