相关论文: Sotopia-RL: Reward Design for Social Intelligence

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However,…

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there…

Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward…

Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in soliciting this feedback, even when faced with ambiguity, which can make their dialogues feel…

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

Signal Temporal Logic (STL) is a powerful formal language for specifying real-time specifications of Cyber-Physical Systems (CPS). Transforming specifications written in natural language into STL formulas automatically has attracted…

Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions within a long trajectory caused the outcome remains difficult. This credit assignment (CA)…

Recently, Large Language Models (LLMs) have made significant progress in IQ-related domains that require careful thinking, such as mathematics and coding. However, enhancing LLMs' cognitive development in social domains, particularly from a…

How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time,…

Large Language Models (LLMs) have recently demonstrated strong potential in generating 'believable human-like' behavior in web environments. Prior work has explored augmenting training data with LLM-synthesized rationales and applying…

Large language models (LLMs) have demonstrated exciting progress in acquiring diverse new capabilities through in-context learning, ranging from logical reasoning to code-writing. Robotics researchers have also explored using LLMs to…

Despite the abundance of prior social strategies possessed by humans, there remains a paucity of research dedicated to their transfer and integration into social agents. Our proposed SOTOPIA-$\Omega$ framework aims to address and bridge…

When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with…

Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents…

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…

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward can be very sparse for it is usually only provided at the end…

Recent advances have shown success in eliciting strong reasoning abilities in multimodal large language models (MLLMs) through rule-based reinforcement learning (RL) with outcome rewards. However, this paradigm typically lacks supervision…