相关论文: Adaptive Alignment: Dynamic Preference Adjustments…

Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world. For this purpose, a desirable solution should properly balance memory stability with learning plasticity, and acquire sufficient…

Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In…

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…

Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement…

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, where models lose previously acquired knowledge…

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

We consider the general problem of learning a predictor that satisfies multiple objectives of interest simultaneously, a broad framework that captures a range of specific learning goals including calibration, regret, and multiaccuracy. We…

Making decisions in complex driving environments is a challenging task for autonomous agents. Imitation learning methods have great potentials for achieving such a goal. Adversarial Inverse Reinforcement Learning (AIRL) is one of the…

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical…

Multi-objective reinforcement learning (MORL) aims at optimising several, often conflicting goals to improve the flexibility and reliability of RL in practical tasks. This is typically achieved by finding a set of diverse, non-dominated…

We develop a novel multi-objective reinforcement learning (MORL) framework to jointly optimize wireless network selection and autonomous driving policies in a multi-band vehicular network operating on conventional sub-6GHz spectrum and…

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Multimodal learning often encounters the under-optimized problem and may perform worse than unimodal learning. Existing approaches attribute this issue to imbalanced learning across modalities and tend to address it through gradient…

As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the…

Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to…

Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional preferences, recent studies have explored multi-dimensional…

This paper presents a model for dynamic adjustment of the motivation degree, using a reinforcement learning approach, in an action selection mechanism previously developed by the authors. The learning takes place in the modification of a…

Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL)…

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…