18 citations · 75 across the 10 of their papers we have counts for
7 papers · 1 filter
Prompting Decision Transformer for Few-Shot Policy Generalization
Mengdi Xu, Yikang Shen, Shun Zhang +4
Humans can leverage prior experience and learn novel tasks from a handful of demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve quick adaptat…
Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training
Peide Huang, Mengdi Xu, Fei Fang +1
Robust Reinforcement Learning (RL) focuses on improving performances under model errors or adversarial attacks, which facilitates the real-life deployment of RL agents. Robust Adve…
Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
Baiming Chen, Zuxin Liu, Jiacheng Zhu +3
Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the…
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
Mengdi Xu, Wenhao Ding, Jiacheng Zhu +3
Continuously learning to solve unseen tasks with limited experience has been extensively pursued in meta-learning and continual learning, but with restricted assumptions such as ac…
Delay-Aware Model-Based Reinforcement Learning for Continuous Control
Baiming Chen, Mengdi Xu, Liang Li +1
Action delays degrade the performance of reinforcement learning in many real-world systems. This paper proposes a formal definition of delay-aware Markov Decision Process and prove…
Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments
Baiming Chen, Mengdi Xu, Zuxin Liu +2
Action and observation delays exist prevalently in the real-world cyber-physical systems which may pose challenges in reinforcement learning design. It is particularly an arduous t…
CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
Wenhao Ding, Mengdi Xu, Ding Zhao
Naturalistic driving trajectories are crucial for the performance of autonomous driving algorithms. However, most of the data is collected in safe scenarios leading to the duplicat…