Search Results for author: Tianhao Wei

Found 8 papers, 5 papers with code

Absolute Policy Optimization

1 code implementation20 Oct 2023 WeiYe Zhao, Feihan Li, Yifan Sun, Rui Chen, Tianhao Wei, Changliu Liu

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios.

Atari Games Continuous Control

State-wise Constrained Policy Optimization

1 code implementation21 Jun 2023 WeiYe Zhao, Rui Chen, Yifan Sun, Tianhao Wei, Changliu Liu

In particular, we introduce the framework of Maximum Markov Decision Process, and prove that the worst-case safety violation is bounded under SCPO.

Autonomous Driving reinforcement-learning +2

GUARD: A Safe Reinforcement Learning Benchmark

1 code implementation23 May 2023 WeiYe Zhao, Rui Chen, Yifan Sun, Ruixuan Liu, Tianhao Wei, Changliu Liu

Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms.

Autonomous Driving reinforcement-learning +2

State-wise Safe Reinforcement Learning: A Survey

no code implementations6 Feb 2023 WeiYe Zhao, Tairan He, Rui Chen, Tianhao Wei, Changliu Liu

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges.

Autonomous Driving reinforcement-learning +3

Safe Control with Neural Network Dynamic Models

1 code implementation3 Oct 2021 Tianhao Wei, Changliu Liu

It has been extensively studied regarding how to derive a safe control law with a control-affine analytical dynamic model.

Online Verification of Deep Neural Networks under Domain Shift or Network Updates

no code implementations24 Jun 2021 Tianhao Wei, Changliu Liu

Although neural networks are widely used, it remains challenging to formally verify the safety and robustness of neural networks in real-world applications.

Management

Safe Control Algorithms Using Energy Functions: A Unified Framework, Benchmark, and New Directions

1 code implementation5 Aug 2019 Tianhao Wei, Changliu Liu

In different methods, the energy function is called a potential function, a safety index, or a barrier function.

Cannot find the paper you are looking for? You can Submit a new open access paper.