A Direct Approximation of AIXI Using Logical State Abstractions S Yang-Zhao, T Wang, KS Ng Advances in Neural Information Processing Systems 35, 36640-36653, 2022 | 4 | 2022 |
Dynamic Knowledge Injection for AIXI Agents S Yang-Zhao, KS Ng, M Hutter Proceedings of the AAAI Conference on Artificial Intelligence 38 (15), 16388 …, 2024 | 1 | 2024 |
Factored conditional filtering: Tracking states and estimating parameters in high-dimensional spaces D Chen, S Yang-Zhao, J Lloyd, KS Ng arXiv preprint arXiv:2206.02178, 2022 | 1 | 2022 |
Conditions on features for temporal difference-like methods to converge M Hutter, S Yang-Zhao, SJ Majeed arXiv preprint arXiv:1905.11702, 2019 | 1 | 2019 |
Sufficient Conditions for Divergence in Projected Bellman Equation Methods S Yang-Zhao The Australian National University, 2018 | | 2018 |