​
Login / Signup
Yunshu Du
ORCID
Publication Activity (10 Years)
Years Active: 2017-2022
Publications (10 Years): 9
Top Topics
Interesting Patterns
Reinforcement Learning
Human Experts
Training Stage
Top Venues
CoRR
Knowl. Eng. Rev.
AAMAS
Neural Comput. Appl.
</>
Publications
</>
Yunshu Du
,
Garrett Warnell
,
Assefaw H. Gebremedhin
,
Peter Stone
,
Matthew E. Taylor
Lucid dreaming for experience replay: refreshing past states with the current policy.
Neural Comput. Appl.
34 (3) (2022)
Yunshu Du
,
Garrett Warnell
,
Assefaw Hadish Gebremedhin
,
Peter Stone
,
Matthew E. Taylor
Lucid Dreaming for Experience Replay: Refreshing Past States with the Current Policy.
CoRR
(2020)
Gabriel Victor de la Cruz
,
Yunshu Du
,
Matthew E. Taylor
Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning.
CoRR
(2019)
Gabriel Victor de la Cruz
,
Yunshu Du
,
Matthew E. Taylor
Pre-training with non-expert human demonstration for deep reinforcement learning.
Knowl. Eng. Rev.
34 (2019)
Yunshu Du
Improving Deep Reinforcement Learning via Transfer.
AAMAS
(2019)
Yunshu Du
,
Assefaw H. Gebremedhin
,
Matthew E. Taylor
Analysis of University Fitness Center Data Uncovers Interesting Patterns, Enables Prediction.
IEEE Trans. Knowl. Data Eng.
31 (8) (2019)
Gabriel Victor de la Cruz
,
Yunshu Du
,
Matthew E. Taylor
Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning.
CoRR
(2018)
Yunshu Du
,
Wojciech M. Czarnecki
,
Siddhant M. Jayakumar
,
Razvan Pascanu
,
Balaji Lakshminarayanan
Adapting Auxiliary Losses Using Gradient Similarity.
CoRR
(2018)
Gabriel Victor de la Cruz
,
Yunshu Du
,
Matthew E. Taylor
Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning.
CoRR
(2017)