Mahammad Humayoo

Segmenting Action-Value Functions over Time Scales in SARSA via TD(Δ)

Mahammad Humayoo, Gengzhong Zheng, Xiaoqing Dong, Wei Huang et autres

In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal balance between bias and variation, primarily due to their dependence on a …

cn (code pays fourni par la source)

Relative importance sampling for off-policy actor-critic in deep reinforcement learning

Mahammad Humayoo, Gengzhong Zheng, Xiaoqing Dong, Liming Miao et autres

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy (π) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. …

cn (code pays fourni par la source)

Segmenting Action-Value Functions Over Time-Scales in SARSA via TD($Δ$)

Mahammad Humayoo

In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal balance between bias and variation, primarily due to their dependence on a …

Time-Scale Separation in Q-Learning: Extending TD($\triangle$) for Action-Value Function Decomposition

Mahammad Humayoo

Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with variance, particularly in the context of long-term rewards. This paper introduces …

SAPPNet: students’ academic performance prediction during COVID-19 using neural network

Naveed Ur Rehman Junejo, Qingsheng Huang, Xiaoqing Dong, Chang Wang et autres

A variety of reasons have made it more difficult for educators and tutors to anticipate students’ performance. Numerous researchers have used various predictive models to identify students who may be at-risk of dropping out early. Additionally, these methods were used to forecast …

cn (code pays fourni par la source)

SLPNet: Student Learning Performance Prediction During the COVID-19 Pandemic via a Deep Neural Network

Naveed Ur Rehman Junejo, Qingsheng Huang, Xiaoqing Dong, Chang Wang et autres

cn (code pays fourni par la source)

Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning

Mahammad Humayoo

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($π$) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. …

Model-free Knockoffs for SLOPE-Adaptive Variable Selection with Controlled False Discovery Rate

Mahammad Humayoo, Xueqi Cheng

Automatic selection of true explanatory variables and controlling fraction of false discovery rate (FDR) in the linear model has received considerable attention in machine learning. The ordered regularization is an important component of the linear model and plays a key role in …

cn (code pays fourni par la source)

Operator Scale Out Using Time Utility Function in Big Data Stream Processing

Mahammad Humayoo, Yanlong Zhai, Yan He, Bingqing Xu et autres

cn (code pays fourni par la source)