no code implementations • 20 Jan 2023 • Chenning Yu, QingBiao Li, Sicun Gao, Amanda Prorok
Though it is complete and optimal, it does not scale well.
no code implementations • 1 Nov 2022 • Yaoguang Zhai, Sicun Gao
The key to Black-Box Optimization is to efficiently search through input regions with potentially widely-varying numerical properties, to achieve low-regret descent and fast progress toward the optima.
1 code implementation • 22 Oct 2022 • Eric Yang Yu, Zhizhen Qin, Min Kyung Lee, Sicun Gao
Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts.
1 code implementation • NeurIPS 2021 • Chenning Yu, Sicun Gao
We propose new learning-based methods for reducing collision checking to accelerate motion planning by training graph neural networks (GNNs) that perform path exploration and path smoothing.
no code implementations • 16 Oct 2022 • Ruipeng Zhang, Chenning Yu, Jingkai Chen, Chuchu Fan, Sicun Gao
Learning-based methods have shown promising performance for accelerating motion planning, but mostly in the setting of static environments.
no code implementations • 24 Aug 2022 • Xiaofan Yu, Yunhui Guo, Sicun Gao, Tajana Rosing
To address the challenges, we propose Self-Supervised ContrAstive Lifelong LEarning without Prior Knowledge (SCALE) which can extract and memorize representations on-the-fly purely from the data continuum.
1 code implementation • 14 Jul 2022 • Hui Shi, Yupeng Gu, Yitong Zhou, Bo Zhao, Sicun Gao, Jishen Zhao
In this paper, we propose the Multi-Interest Preference (MIP) model, an approach that not only produces multi-interest for users by using the user's sequential engagement more effectively but also automatically learns a set of weights to represent the preference over each embedding so that the candidates can be retrieved from each interest proportionally.
1 code implementation • 16 Dec 2021 • Hui Shi, Sicun Gao, Yuandong Tian, Xinyun Chen, Jishen Zhao
With the forced decomposition, we show that the performance upper bounds of LSTM and Transformer in learning CFL are close: both of them can simulate a stack and perform stack operation along with state transitions.
no code implementations • 14 Sep 2021 • Charles Dawson, Zengyi Qin, Sicun Gao, Chuchu Fan
Safety and stability are common requirements for robotic control systems; however, designing safe, stable controllers remains difficult for nonlinear and uncertain models.
no code implementations • 2 Dec 2020 • Tong Huang, Sicun Gao, Le Xie
Case studies suggest that the proposed method can address networked microgrids with heterogeneous interface dynamics, and in comparison with conventional methods that are based on quadratic Lyapunov functions, can characterize the security regions with much less conservativeness.
no code implementations • ICML 2020 • Yuda Song, Aditi Mavalankar, Wen Sun, Sicun Gao
The high sample complexity of reinforcement learning challenges its use in practice.
1 code implementation • NeurIPS 2019 • Ya-Chien Chang, Nima Roohi, Sicun Gao
We propose new methods for learning control policies and neural network Lyapunov functions for nonlinear control problems, with provable guarantee of stability.
no code implementations • 25 Sep 2019 • Aditi Mavalankar, Sicun Gao
Many practical robot locomotion tasks require agents to use control policies that can be parameterized by goals.
1 code implementation • 28 Mar 2019 • Quan Vuong, Sharad Vikram, Hao Su, Sicun Gao, Henrik I. Christensen
A human-specified design choice in domain randomization is the form and parameters of the distribution of simulated environments.
no code implementations • 13 Feb 2018 • Jeevana Priya Inala, Sicun Gao, Soonho Kong, Armando Solar-Lezama
In this paper, we present ReaS, a technique that combines numerical optimization with SAT solving to synthesize unknowns in a program that involves discrete and floating point computation.