MICo: Improved representations via sampling-based state similarity for Markov decision processes PS Castro*, T Kastner*, P Panangaden, M Rowland Advances in Neural Information Processing Systems 34, 30113-30126, 2021 | 70 | 2021 |
Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning T Kastner, MA Erdogdu, A Farahmand Advances in Neural Information Processing Systems 36, 2023 | 9 | 2023 |
A Kernel Perspective on Behavioural Metrics for Markov Decision Processes PS Castro, T Kastner, P Panangaden, M Rowland Transactions on Machine Learning Research, 2023 | 6 | 2023 |
When does self-prediction help? understanding auxiliary tasks in reinforcement learning C Voelcker, T Kastner, I Gilitschenski, A Farahmand arXiv preprint arXiv:2406.17718, 2024 | 2 | 2024 |
State similarity metrics in reinforcement learning T Kastner McGill University, 2022 | 1 | 2022 |