no code implementations • 30 Oct 2022 • Fuyang Li, Jiying Zhang, Xi Xiao, Bin Zhang, Dijun Luo
This paper proposes a two-phase paradigm to aggregate comprehensive information on discrete structures leading to a Discount Markov Diffusion Learnable Kernel (DMDLK).
no code implementations • 29 Jan 2022 • Liu Liu, Ziyang Tang, Lanqing Li, Dijun Luo
We consider offline Imitation Learning from corrupted demonstrations where a constant fraction of data can be noise or even arbitrary outliers.
no code implementations • 26 Aug 2021 • Wanpeng Zhang, Xiaoyan Cao, Yao Yao, Zhicheng An, Xi Xiao, Dijun Luo
In this paper, we present a model-based robust RL framework for autonomous greenhouse control to meet the sample efficiency and safety challenges.
no code implementations • 3 Aug 2021 • Wanpeng Zhang, Xi Xiao, Yao Yao, Mingzhe Chen, Dijun Luo
MBDP consists of two kinds of dropout mechanisms, where the rollout-dropout aims to improve the robustness with a small cost of sample efficiency, while the model-dropout is designed to compensate for the lost efficiency at a slight expense of robustness.
1 code implementation • 6 Jul 2021 • Xiaoyan Cao, Yao Yao, Lanqing Li, Wanpeng Zhang, Zhicheng An, Zhong Zhang, Li Xiao, Shihui Guo, Xiaoyu Cao, Meihong Wu, Dijun Luo
However, the optimal control of autonomous greenhouses is challenging, requiring decision-making based on high-dimensional sensory data, and the scaling of production is limited by the scarcity of labor capable of handling this task.
1 code implementation • 5 Jul 2021 • Yao Yao, Li Xiao, Zhicheng An, Wanpeng Zhang, Dijun Luo
Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics.
no code implementations • 25 Feb 2021 • Rui Yang, Jiafei Lyu, Yu Yang, Jiangpeng Yan, Feng Luo, Dijun Luo, Lanqing Li, Xiu Li
Two main challenges in multi-goal reinforcement learning are sparse rewards and sample inefficiency.
no code implementations • 22 Feb 2021 • Lanqing Li, Yuanhao Huang, Mingzhe Chen, Siteng Luo, Dijun Luo, Junzhou Huang
Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications.
1 code implementation • ICLR 2021 • Lanqing Li, Rui Yang, Dijun Luo
In this work, we enforce behavior regularization on learned policy as a general approach to offline RL, combined with a deterministic context encoder for efficient task inference.
no code implementations • CVPR 2014 • Dijun Luo, Heng Huang
After that, we employ an embedded manifold denoising approach with the adaptive kernel to segment the motion of rigid and non-rigid objects.
no code implementations • NeurIPS 2012 • Dijun Luo, Heng Huang, Feiping Nie, Chris H. Ding
In many graph-based machine learning and data mining approaches, the quality of the graph is critical.