| 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 | 169 | 2018 |
| 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 | 45 | 2019 |
| 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 | 23 | 2016 |
| 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 | 14 | 2018 |
| 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 | 10 | 2022 |
| 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 | 8 | 2016 |
| Improving deep reinforcement learning via transfer Y Du Proceedings of the 18th International Conference on Autonomous Agents and …, 2019 | 5 | 2019 |
| 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 | 3 | 2016 |
| 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 | 2 | 2019 |
| 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 |
Matthew E. TaylorProfessor, University of AlbertaVerified email at ualberta.ca
