Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Linrui Zhang

Linrui Zhang

Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

Dec 14, 2022
Linrui Zhang, Zichen Yan, Li Shen, Shoujie Li, Xueqian Wang, Dacheng Tao

Figure 1 for Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

Figure 2 for Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

Figure 3 for Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

Figure 4 for Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning

* The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

Access Paper or Ask Questions

Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

Dec 12, 2022
Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang, Dacheng Tao

Figure 1 for Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

Figure 2 for Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

Figure 3 for Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

Figure 4 for Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

* 37th AAAI Conference on Artificial Intelligence (AAAI-23)

Access Paper or Ask Questions

Constrained Update Projection Approach to Safe Policy Optimization

Sep 15, 2022
Long Yang, Jiaming Ji, Juntao Dai, Linrui Zhang, Binbin Zhou, Pengfei Li, Yaodong Yang, Gang Pan

Figure 1 for Constrained Update Projection Approach to Safe Policy Optimization

Figure 2 for Constrained Update Projection Approach to Safe Policy Optimization

Figure 3 for Constrained Update Projection Approach to Safe Policy Optimization

Figure 4 for Constrained Update Projection Approach to Safe Policy Optimization

* Accepted by NeurIPS2022. arXiv admin note: substantial text overlap with arXiv:2202.07565; text overlap with arXiv:2002.06506 by other authors

Access Paper or Ask Questions

SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

Jun 17, 2022
Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang

Figure 1 for SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

Figure 2 for SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

Figure 3 for SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

Figure 4 for SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

* The 1st Workshop on Safe Learning for Autonomous Driving (SL4AD) with ICML 2022

Access Paper or Ask Questions