相关论文: A Safe Preference Learning Approach for Personaliz…

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model among groups (e.g., male or female) of diverse sensitive features. However, there is a trade-off between model performance and fairness,…

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

In this paper, we propose a Q-learning based decision-making framework to improve the safety and efficiency of Autonomous Vehicles when they encounter other maliciously behaving vehicles while passing through unsignalized intersections. In…

For safe operation, autonomous vehicles have to obey traffic rules that are set forth in legal documents formulated in natural language. Temporal logic is a suitable concept to formalize such traffic rules. Still, temporal logic rules often…

Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect…

This paper investigates the problem of designing control policies that satisfy high-level specifications described by signal temporal logic (STL) in unknown, stochastic environments. While many existing works concentrate on optimizing the…

Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the area of NLP and personalization. In this survey, we present…

Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. In particular, batch packing is commonly used in pre-training and supervised fine-tuning…

We present GradSTL, the first fully comprehensive implementation of signal temporal logic (STL) suitable for integration with neurosymbolic learning. In particular, GradSTL can successfully evaluate any STL constraint over any signal,…

We introduce a new family of temporal logics intended for specifications in motion planning (MP). It builds upon the signal temporal logic (STL), which is a linear-time logic over real-valued signals that possess quantitative semantics and…

We study feedback motion planning for continuous-time stochastic nonlinear systems under signal temporal logic (STL) specifications. We propose a framework that synthesizes control policies for chance-constrained STL trajectory optimization…

Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to differentiate between correct and incorrect code. Recent…

Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which overlooks diverse preferences and limits…

Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated…

One of the primary goals of statistical precision medicine is to learn optimal individualized treatment rules (ITRs). The classification-based, or machine learning-based, approach to estimating optimal ITRs was first introduced in…

Many autonomous systems, such as robots and self-driving cars, involve real-time decision making in complex environments, and require prediction of future outcomes from limited data. Moreover, their decisions are increasingly required to be…

A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing safe RL paradigms inherently struggle to achieve this…

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual…

We are interested in the design of autonomous robot behaviors that learn the preferences of users over continued interactions, with the goal of efficiently executing navigation behaviors in a way that the user expects. In this paper, we…