Related papers: Reinforcement World Model Learning for LLM-based A…

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a…

World models simulate dynamic environments, enabling agents to interact with diverse input modalities. Although recent advances have improved the visual quality and temporal consistency of video world models, their ability of accurately…

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework…

Reinforcement Learning (RL) plays a crucial role in advancing autonomous driving technologies by maximizing reward functions to achieve the optimal policy. However, crafting these reward functions has been a complex, manual process in many…

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…

Natural language can offer a concise and human-interpretable means of specifying reinforcement learning (RL) tasks. The ability to extract rewards from a language instruction can enable the development of robotic systems that can learn from…

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle…

Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavior can emerge requires expert knowledge, especially for…

Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requires a complex reward design for each task. In contrast,…

While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in mathematical form. Such specifications demand domain…

In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risky. However, designing dense reward signals for offline…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

When we design and deploy an Reinforcement Learning (RL) agent, reward functions motivates agents to achieve an objective. An incorrect or incomplete specification of the objective can result in behavior that does not align with human…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…