31 citations · 67 across the 10 of their papers we have counts for
10 papers
Multi-Abstractive Neural Controller: An Efficient Hierarchical Control Architecture for Interactive Driving
Xiao Li, Igor Gilitschenski, Guy Rosman +2
As learning-based methods make their way from perception systems to planning/control stacks, robot control systems have started to enjoy the benefits that data-driven methods provi…
Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic
Qijun Luo, Xiao Li
Decentralized Actor-Critic (AC) algorithms have been widely utilized for multi-agent reinforcement learning (MARL) and have achieved remarkable success. Apart from its empirical su…
BarrierNet: A Safety-Guaranteed Layer for Neural Networks
Wei Xiao, Ramin Hasani, Xiao Li +1
This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems. CBFs are usually overly conservative…
The Logical Options Framework
Brandon Araki, Xiao Li, Kiran Vodrahalli +3
Learning composable policies for environments with complex rules and tasks is a challenging problem. We introduce a hierarchical reinforcement learning framework called the Logical…
Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions
Xiao Li, Calin Belta
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucia…
Automata Guided Reinforcement Learning With Demonstrations
Xiao Li, Yao Ma, Calin Belta
Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functio…
Automata-Guided Hierarchical Reinforcement Learning for Skill Composition
Xiao Li, Yao Ma, Calin Belta
Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task. We present a framework tha…
A Policy Search Method For Temporal Logic Specified Reinforcement Learning Tasks
Xiao Li, Yao Ma, Calin Belta
Reward engineering is an important aspect of reinforcement learning. Whether or not the user's intentions can be correctly encapsulated in the reward function can significantly imp…
Reinforcement Learning With Temporal Logic Rewards
Xiao Li, Cristian-Ioan Vasile, Calin Belta
Reinforcement learning (RL) depends critically on the choice of reward functions used to capture the de- sired behavior and constraints of a robot. Usually, these are handcrafted b…
A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks
Xiao Li, Calin Belta
Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon and the inverted helicopter flight. However, little effort has been put into devel…