2021

  1. Reward-Weighted Regression Converges to a Global Optimum Štrupl, Miroslav, Faccio, Francesco, Ashley, Dylan R., Srivastava, Rupesh Kumar, and Schmidhuber, Jürgen In arXiv [Abstract] [arXiv] [Code]
  2. Does the Adam Optimizer Exacerbate Catastrophic Forgetting? Ashley, Dylan R., Ghiassian, Sina, and Sutton, Richard S. In arXiv [Abstract] [arXiv] [Code]
  3. Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search Ashley, Dylan R., Kanervisto, Anssi, and Bennett, Brendan In Proceedings of the Conference of the ACH Special Interest Group on Harry Q. Bovik [Abstract] [arXiv] [PDF] [Code]

2020

  1. Understanding Forgetting in Artificial Neural Networks Ashley, Dylan R. Master’s thesis, University of Alberta [Abstract] [PDF] [Code] [Slides]
  2. Universal Successor Features for Transfer Reinforcement Learning Ma, Chen, Ashley, Dylan R., Wen, Junfeng, and Bengio, Yoshua In arXiv [Abstract] [arXiv]

2019

  1. Learning to Select Mates in Evolving Non-playable Characters Ashley, Dylan R., Chockalingam, Valliappa, Kuzma, Braedy, and Bulitko, Vadim In Proceedings of the IEEE Conference on Games [Abstract] [PDF] [Slides]
  2. Learning to Select Mates in Artificial Life Ashley, Dylan R., Chockalingam, Valliappa, Kuzma, Braedy, and Bulitko, Vadim In Proceedings of the Genetic and Evolutionary Computation Conference Companion [Abstract] [PDF] [Code]

2018

  1. Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return Sherstan, Craig, Ashley, Dylan R., Bennett, Brendan, Young, Kenny, White, Adam, White, Martha, and Sutton, Richard S. In Proceedings of the Conference on Uncertainty in Artificial Intelligence [Abstract] [PDF] [SUP] [Code] [Poster] [Slides]
  2. The Alberta Workloads for the SPEC CPU 2017 Benchmark Suite Amaral, José Nelson, Borin, Edson, Ashley, Dylan R., Benedicto, Caian, Colp, Elliot, Hoffmam, Joao Henrique Stange, Karpoff, Marcus, Ochoa, Erick, Redshaw, Morgan, and Rodrigues, Raphael Ernani In Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software [Abstract] [PDF] [Code]
  3. Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods Sherstan, Craig, Bennett, Brendan, Young, Kenny, Ashley, Dylan R., White, Adam, White, Martha, and Sutton, Richard S. In arXiv [Abstract] [arXiv]