117 citations · 117 across the 1 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2018
ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models
Yueh-Hua Wu, Fan-Yun Sun, Yen-Yu Chang +1
This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how…
cs.LG2018
A Memory-Network Based Solution for Multivariate Time-Series Forecasting
Yen-Yu Chang, Fan-Yun Sun, Yueh-Hua Wu +1
Multivariate time series forecasting is extensively studied throughout the years with ubiquitous applications in areas such as finance, traffic, environment, etc. Still, concerns h…