11 papers
Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
Carl Qi, Weijun Dong, Xiaojie Wang +8
Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can improve these…
LIMBO: Learning and Internalizing Model-Free Barrier Objectives for Agile and Safe Whole-Body Control
Jake Gonzales, Arturo Flores Alvarez, Yu-Ming Chen +3
Safe whole-body control requires coordinating collision avoidance and balance under high-dimensional, nonlinear dynamics--making safety certificates difficult to design and reuse a…
Adaptive Calibration in Non-Stationary Environments
Junyan Liu, Haipeng Luo, Lillian J. Ratliff
Making calibrated online predictions is a central challenge in modern AI systems. Much of the existing literature focuses on fully adversarial environments where outcomes may be ar…
Structure from Strategic Interaction & Uncertainty: Risk Sensitive Games for Robust Preference Learning
Max Horwitz, Jake Gonzales, Eric Mazumdar +1
A growing line of work reframes preference-based fine-tuning of large language models game-theoretically: Nash Learning from Human Feedback (NLHF) recasts the problem as a zero-sum…
Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control
Jake Gonzales, Kazuki Mizuta, Karen Leung +1
In this paper, we present a novel probabilistic safe control framework for human-robot interaction that combines control barrier functions (CBFs) with conformal risk control to pro…
Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation
Junyan Liu, Haipeng Luo, Zihan Zhang +1
We study online learning in two-player uninformed Markov games, where the opponent's actions and policies are unobserved. In this setting, Tian et al. (2021) show that achieving no…
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
Shirui Chen, Cole Harrison, Ying-Chun Lee +6
General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.…
Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
Junyan Liu, Ziyun Chen, Kun Wang +2
We study the Pandora's Box problem in an online learning setting with semi-bandit feedback. In each round, the learner sequentially pays to open up to boxes with unknown reward…
A Learning Algorithm That Attains the Human Optimum in a Repeated Human-Machine Interaction Game
Jason T. Isa, Lillian J. Ratliff, Samuel A. Burden
When humans interact with learning-based control systems, a common goal is to minimize a cost function known only to the human. For instance, an exoskeleton may adapt its assistanc…
Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
Junyan Liu, Lillian J. Ratliff
We study the repeated principal-agent bandit game, where the principal indirectly interacts with the unknown environment by proposing incentives for the agent to play arms. Most ex…
Effect of Adaptation Rate and Cost Display in a Human-AI Interaction Game
Jason T. Isa, Bohan Wu, Qirui Wang +4
As interactions between humans and AI become more prevalent, it is critical to have better predictors of human behavior in these interactions. We investigated how changes in the AI…