Publications
2024
- Distributional Pareto-Optimal Multi-Objective Reinforcement LearningAdvances in Neural Information Processing Systems, 2024
- IGOR: Image-goal Representations Are the Atomic Control Units for Foundation Models in Embodied AIarXiv preprint arXiv:2411.00785, 2024
2023
- Asking Before Acting: Gather Information in Embodied Decision Making with Language ModelsarXiv preprint arXiv:2305.15695, 2023
- Preference-conditioned Pixel-based AI Agent For Game TestingIn 2023 IEEE Conference on Games (CoG), 2023
- IG-Net: Image-Goal Network for Offline Visual Navigation on A Large-Scale Game Map2023
2022
- An adaptive deep rl method for non-stationary environments with piecewise stable contextAdvances in Neural Information Processing Systems, 2022
2021
- Demonstration Actor CriticNeurocomputing, 2021
- Independence-aware Advantage EstimationIn Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, 2021
- Distributional Reinforcement Learning for Multi-Dimensional Reward FunctionsAdvances in Neural Information Processing Systems, 2021