34 citations · 48 across the 16 of their papers we have counts for
17 papers
GPT-Red: Automated Red Teaming via Self-Play at Scale
Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal +15
We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluat…
Factored Latent Action World Models
Zizhao Wang, Chang Shi, Jiaheng Hu +4
Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for u…
Adversarial Reinforcement Learning for Large Language Model Agent Safety
Zizhao Wang, Dingcheng Li, Vaishakh Keshava +4
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, wh…
Dyn-O: Building Structured World Models with Object-Centric Representations
Zizhao Wang, Kaixin Wang, Li Zhao +2
World models aim to capture the dynamics of the environment, enabling agents to predict and plan for future states. In most scenarios of interest, the dynamics are highly centered…
SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions
Zizhao Wang, Jiaheng Hu, Caleb Chuck +5
Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised…
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
Jiaheng Hu, Zizhao Wang, Peter Stone +1
A hallmark of intelligent agents is the ability to learn reusable skills purely from unsupervised interaction with the environment. However, existing unsupervised skill discovery m…
Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination
Saad Abdul Ghani, Zizhao Wang, Peter Stone +1
This paper introduces Dynamic Learning from Learned Hallucination (Dyna-LfLH), a self-supervised method for training motion planners to navigate environments with dense and dynamic…
Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning
Zizhao Wang, Caroline Wang, Xuesu Xiao +2
Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of…
ELDEN: Exploration via Local Dependencies
Jiaheng Hu, Zizhao Wang, Peter Stone +1
Tasks with large state space and sparse rewards present a longstanding challenge to reinforcement learning. In these tasks, an agent needs to explore the state space efficiently un…
Learning to Correct Mistakes: Backjumping in Long-Horizon Task and Motion Planning
Yoonchang Sung, Zizhao Wang, Peter Stone
As robots become increasingly capable of manipulation and long-term autonomy, long-horizon task and motion planning problems are becoming increasingly important. A key challenge in…
Autonomous Ground Navigation in Highly Constrained Spaces: Lessons learned from The BARN Challenge at ICRA 2022
Xuesu Xiao, Zifan Xu, Zizhao Wang +14
The BARN (Benchmark Autonomous Robot Navigation) Challenge took place at the 2022 IEEE International Conference on Robotics and Automation (ICRA 2022) in Philadelphia, PA. The aim…
Causal Dynamics Learning for Task-Independent State Abstraction
Zizhao Wang, Xuesu Xiao, Zifan Xu +2
Learning dynamics models accurately is an important goal for Model-Based Reinforcement Learning (MBRL), but most MBRL methods learn a dense dynamics model which is vulnerable to sp…
APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback
Zizhao Wang, Xuesu Xiao, Garrett Warnell +1
Classical autonomous navigation systems can control robots in a collision-free manner, oftentimes with verifiable safety and explainability. When facing new environments, however,…
From Agile Ground to Aerial Navigation: Learning from Learned Hallucination
Zizhao Wang, Xuesu Xiao, Alexander J Nettekoven +5
This paper presents a self-supervised Learning from Learned Hallucination (LfLH) method to learn fast and reactive motion planners for ground and aerial robots to navigate through…
APPL: Adaptive Planner Parameter Learning
Xuesu Xiao, Zizhao Wang, Zifan Xu +5
While current autonomous navigation systems allow robots to successfully drive themselves from one point to another in specific environments, they typically require extensive manua…
APPLI: Adaptive Planner Parameter Learning From Interventions
Zizhao Wang, Xuesu Xiao, Bo Liu +2
While classical autonomous navigation systems can typically move robots from one point to another safely and in a collision-free manner, these systems may fail or produce suboptima…
APPLR: Adaptive Planner Parameter Learning from Reinforcement
Zifan Xu, Gauraang Dhamankar, Anirudh Nair +5
Classical navigation systems typically operate using a fixed set of hand-picked parameters (e.g. maximum speed, sampling rate, inflation radius, etc.) and require heavy expert re-t…