Follow
Yunshu Du
Yunshu Du
Sony AI | Ph.D. Computer Science
Verified email at sony.com - Homepage
Title
Cited by
Cited by
Year
Adapting Auxiliary Losses Using Gradient Similarity
Y Du, WM Czarnecki, SM Jayakumar, R Pascanu, B Lakshminarayanan
The Continual learning Workshop at NeurIPS 2018, Montreal, QC, Canada, 2018
1692018
Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning
GV de la Cruz, Y Du, ME Taylor
The Adaptive Learning Agents workshop at the Federated AI Meeting 2018 …, 2018
71*2018
Pre-training with non-expert human demonstration for deep reinforcement learning
GV de la Cruz, Y Du, ME Taylor
The Knowledge Engineering Review 34, 2019
452019
Initial Progress in Transfer for Deep Reinforcement Learning Algorithms
Y Du, GV de la Cruz, J Irwin, ME Taylor
The Deep Reinforcement Learning: Frontiers and Challenges Workshop at IJCAI …, 2016
232016
Analysis of University Fitness Center Data Uncovers Interesting Patterns, Enables Prediction
Y Du, A Gebremedhin, ME Taylor
IEEE Transactions on Knowledge and Data Engineering 31 (8), 1478 - 1490, 2018
142018
Lucid dreaming for experience replay: refreshing past states with the current policy
Y Du, G Warnell, A Gebremedhin, P Stone, ME Taylor
Neural Computing and Applications 34 (3), 1687-1712, 2022
102022
Initial progress in transfer for deep reinforcement learning algorithms
G De la Cruz, Y Du, J Irwin, M Taylor
25th International Joint Conference on Artificial Intelligence (IJCAI) 7, 2016
82016
Improving deep reinforcement learning via transfer
Y Du
Proceedings of the 18th International Conference on Autonomous Agents and …, 2019
52019
Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning
GV de la Cruz, Y Du, ME Taylor
The Adaptive and Learning Agents Workshop at AAMAS 2019, 2019
5*2019
Work In-progress: Mining the Student Data for Fitness
Y Du, ME Taylor
The 12th International Workshop on Agents and Data Mining Interaction (ADMI …, 2016
32016
Pre-training neural networks with human demonstrations for deep reinforcement learning
ME TAYLOR, GV DE LA CRUZ, Y DU
US Patent App. 16/264,625, 2019
22019
Transfer in Deep Reinforcement Learning: How an Agent Can Leverage Knowledge from Another Agent, a Human, or Itself
Y Du
Washington State University, 2021
2021
Work-in-progress: Corrected Self Imitation Learning via Demonstrations
Y Du, G Warnell, A Gebremedhin, P Stone, ME Taylor
The Adaptive and Learning Agents Workshop at AAMAS 2020, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–13