Yunshu Du

Adapting Auxiliary Losses Using Gradient Similarity pdf

Razvan Pascanu, Wojciech Czarnecki, Balaji Lakshminarayanan, 2018, ArXiv.

Initial Progress in Transfer for Deep Reinforcement Learning Algorithms

Matthew E. Taylor, Yunshu Du, G. Cruz, 2016 .

Work In-progress : Mining the Student Data for Fitness

Matthew E. Taylor, Yunshu Du, 2016 .

Work-in-progress: Corrected Self Imitation Learning via Demonstrations

Matthew E. Taylor, P. Stone, Garrett Warnell, 2020 .

Lucid dreaming for experience replay: refreshing past states with the current policy

Matthew E. Taylor, P. Stone, Garrett Warnell, 2020, Neural Computing and Applications.

HetEOTL: An Algorithm for Heterogeneous Online Transfer Learning

Ming Xu, Qian Chen, Chong-Jun Wang, 2018, 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI).

Pre-training with non-expert human demonstration for deep reinforcement learning

Matthew E. Taylor, Gabriel Victor de la Cruz, Yunshu Du, 2018, The Knowledge Engineering Review.

Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning pdf

Matthew E. Taylor, Gabriel Victor de la Cruz, Yunshu Du, 2017, ArXiv.

Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning pdf

Matthew E. Taylor, Gabriel Victor de la Cruz, Yunshu Du, 2019, ArXiv.

Noise-Robust Bidirectional Learning with Dynamic Sample Reweighting

Yunshu Du, Shao-Yuan Li, Mingshan Xie, 2022, ArXiv.

Pre-training with non-expert human demonstration for deep reinforcement learning

Matthew E. Taylor, Yunshu Du, G. V. D. L. Cruz, 2018, Knowledge engineering review (Print).