 BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RLInternational Conference on Learning Representations (ICLR), 2025 |
 Agent-state based policies in POMDPs: Beyond belief-state MDPsIEEE Conference on Decision and Control (CDC), 2024 |
 Conditions on Preference Relations that Guarantee the Existence of
Optimal PoliciesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 A Definition of Continual Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 |
 Bayesian Reinforcement Learning with Limited Cognitive LoadOpen Mind (OM), 2023 |
 Settling the Reward HypothesisInternational Conference on Machine Learning (ICML), 2022 |
 Planning to the Information Horizon of BAMDPs via Epistemic State
AbstractionNeural Information Processing Systems (NeurIPS), 2022 |
