no code implementations • 16 May 2022 • Dongjie Yu, Haitong Ma, Shengbo Eben Li, Jianyu Chen
We characterize the feasible set by the established self-consistency condition, then a safety value function can be learned and used as constraints in CRL.
no code implementations • 23 Mar 2022 • Qiushan Guo, Yao Mu, Jianyu Chen, Tianqi Wang, Yizhou Yu, Ping Luo
Further, we overcome these challenges by introducing a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
no code implementations • 29 Jan 2022 • YuHeng Lei, Jianyu Chen, Shengbo Eben Li, Sifa Zheng
Zeroth-order optimization methods and policy gradient based first-order methods are two promising alternatives to solve reinforcement learning (RL) problems with complementary advantages.
no code implementations • NeurIPS 2021 • Yao Mu, Yuzheng Zhuang, Bin Wang, Guangxiang Zhu, Wulong Liu, Jianyu Chen, Ping Luo, Shengbo Li, Chongjie Zhang, Jianye Hao
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment.
no code implementations • 25 Nov 2021 • Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, Wenchao Sun, Jianyu Chen
Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger.
no code implementations • 15 Nov 2021 • Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, Jianyu Chen
This paper proposes a novel approach that simultaneously synthesizes the energy-function-based safety certificate and learns the safe control policy with CRL.
no code implementations • 29 Sep 2021 • Xiaoyu Chen, Yao Mu, Ping Luo, Shengbo Eben Li, Jianyu Chen
Partially Observable Markov Decision Process (POMDP) provides a principled and generic framework to model real world sequential decision making processes but yet remains unsolved, especially for high dimensional continuous space and unknown models.
no code implementations • 26 Aug 2021 • Baiyu Peng, Jingliang Duan, Jianyu Chen, Shengbo Eben Li, Genjin Xie, Congsheng Zhang, Yang Guan, Yao Mu, Enxin Sun
Based on this, the penalty method is formulated as a proportional controller, and the Lagrangian method is formulated as an integral controller.
1 code implementation • 22 May 2021 • Haitong Ma, Yang Guan, Shegnbo Eben Li, Xiangteng Zhang, Sifa Zheng, Jianyu Chen
The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks.
1 code implementation • 16 May 2021 • Yu Shen, Sijie Zhu, Taojiannan Yang, Chen Chen, Delu Pan, Jianyu Chen, Liang Xiao, Qian Du
With a pair of pre- and post-disaster satellite images, building damage assessment aims at predicting the extent of damage to buildings.
Ranked #1 on
2D Semantic Segmentation
on xBD
1 code implementation • 2 Mar 2021 • Haitong Ma, Jianyu Chen, Shengbo Eben Li, Ziyu Lin, Yang Guan, Yangang Ren, Sifa Zheng
Model information can be used to predict future trajectories, so it has huge potential to avoid dangerous region when implementing reinforcement learning (RL) on real-world tasks, like autonomous driving.
2 code implementations • 23 Feb 2021 • Yang Guan, Jingliang Duan, Shengbo Eben Li, Jie Li, Jianyu Chen, Bo Cheng
MPG contains two types of PG: 1) data-driven PG, which is obtained by directly calculating the derivative of the learned Q-value function with respect to actions, and 2) model-driven PG, which is calculated using BPTT based on the model-predictive return.
no code implementations • 17 Feb 2021 • Baiyu Peng, Yao Mu, Jingliang Duan, Yang Guan, Shengbo Eben Li, Jianyu Chen
Taking a control perspective, we first interpret the penalty method and the Lagrangian method as proportional feedback and integral feedback control, respectively.
no code implementations • 16 Feb 2021 • Yuhang Zhang, Yao Mu, Yujie Yang, Yang Guan, Shengbo Eben Li, Qi Sun, Jianyu Chen
Reinforcement learning has shown great potential in developing high-level autonomous driving.
no code implementations • 17 Jan 2021 • Jinning Li, Liting Sun, Jianyu Chen, Masayoshi Tomizuka, Wei Zhan
To address this challenge, we propose a hierarchical behavior planning framework with a set of low-level safe controllers and a high-level reinforcement learning algorithm (H-CtRL) as a coordinator for the low-level controllers.
no code implementations • 19 Dec 2020 • Baiyu Peng, Yao Mu, Yang Guan, Shengbo Eben Li, Yuming Yin, Jianyu Chen
Safety is essential for reinforcement learning (RL) applied in real-world situations.
1 code implementation • 2 Aug 2020 • Yu Shen, Sijie Zhu, Chen Chen, Qian Du, Liang Xiao, Jianyu Chen, Delu Pan
Therefore, to incorporate the long-range contextual information, a deep fully convolutional network (FCN) with an efficient non-local module, named ENL-FCN, is proposed for HSI classification.
1 code implementation • 21 Mar 2020 • Jianyu Chen, Zhuo Xu, Masayoshi Tomizuka
Current autonomous driving systems are composed of a perception system and a decision system.
2 code implementations • 23 Jan 2020 • Jianyu Chen, Shengbo Eben Li, Masayoshi Tomizuka
A sequential latent environment model is introduced and learned jointly with the reinforcement learning process.
no code implementations • 11 Nov 2019 • Chen Tang, Jianyu Chen, Masayoshi Tomizuka
Current methods for long-term trajectory prediction cannot guarantee the physical feasibility of predicted distribution.
1 code implementation • 19 Aug 2019 • Jie Li, Haifeng Liu, Chuanghua Gui, Jianyu Chen, Zhenyun Ni, Ning Wang
We present the design and implementation of a visual search system for real time image retrieval on JD. com, the world's third largest and China's largest e-commerce site.
no code implementations • 6 Jun 2019 • Long Xin, Pin Wang, Ching-Yao Chan, Jianyu Chen, Shengbo Eben Li, Bo Cheng
As autonomous vehicles (AVs) need to interact with other road users, it is of importance to comprehensively understand the dynamic traffic environment, especially the future possible trajectories of surrounding vehicles.
1 code implementation • 20 Apr 2019 • Jianyu Chen, Bodi Yuan, Masayoshi Tomizuka
Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions.