no code implementations • 31 Oct 2023 • Haohong Lin, Wenhao Ding, Zuxin Liu, Yaru Niu, Jiacheng Zhu, Yuming Niu, Ding Zhao
However, maintaining safety in diverse safety-critical scenarios remains a significant challenge due to long-tailed and unforeseen scenarios absent from offline datasets.
3 code implementations • 15 Jun 2023 • Zuxin Liu, Zijian Guo, Haohong Lin, Yihang Yao, Jiacheng Zhu, Zhepeng Cen, Hanjiang Hu, Wenhao Yu, Tingnan Zhang, Jie Tan, Ding Zhao
This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and deployment phases.
1 code implementation • 19 Jul 2022 • Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and discovering cause-and-effect relations.
no code implementations • CVPR 2022 • Huajie Shao, Yifei Yang, Haohong Lin, Longzhong Lin, Yizhuo Chen, Qinmin Yang, Han Zhao
It has shown success in a variety of applications, such as image generation, disentangled representation learning, and language modeling.
no code implementations • 26 Oct 2021 • Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems.
no code implementations • 8 Jun 2021 • Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness.
no code implementations • 23 Feb 2021 • Huajie Shao, Jun Wang, Haohong Lin, Xuezhou Zhang, Aston Zhang, Heng Ji, Tarek Abdelzaher
The algorithm is injected into a Conditional Variational Autoencoder (CVAE), allowing \textit{Apex} to control both (i) the order of keywords in the generated sentences (conditioned on the input keywords and their order), and (ii) the trade-off between diversity and accuracy.
no code implementations • 15 Sep 2020 • Huajie Shao, Haohong Lin, Qinmin Yang, Shuochao Yao, Han Zhao, Tarek Abdelzaher
Existing methods, such as $\beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement.