相关论文: PrefCLM: Enhancing Preference-based Reinforcement …

Reinforcement learning (RL) is increasingly being used in the healthcare domain, particularly for the development of personalized health adaptive interventions. Inspired by the success of Large Language Models (LLMs), we are interested in…

This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both…

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained…

Deep reinforcement learning (DRL) shows promising potential for autonomous driving decision-making. However, DRL demands extensive computational resources to achieve a qualified policy in complex driving scenarios due to its low learning…

Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…

Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either…

This paper introduces a novel pipeline for summarising timelines of events reported by multiple news sources. Transformer-based models for abstractive summarisation generate coherent and concise summaries of long documents but can fail to…

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference…

Understanding human preferences is crucial for improving foundation models and building personalized AI systems. However, preferences are inherently diverse and complex, making it difficult for traditional reward models to capture their…

Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically…

Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. RL from AI Feedback (RLAIF), introduced in…

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

The development of intelligent robots requires control policies that can handle dynamic environments and evolving tasks. Pre-training reinforcement learning has emerged as an effective approach to address these demands by enabling robots to…

Learning from human involvement aims to incorporate the human subject to monitor and correct agent behavior errors. Although most interactive imitation learning methods focus on correcting the agent's action at the current state, they do…

Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which primarily based on training embeddings, face various challenges associated…

Modern recommender systems aim to improve user experience. As reinforcement learning (RL) naturally fits this objective -- maximizing an user's reward per session -- it has become an emerging topic in recommender systems. Developing…

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…