Related papers: LgTS: Dynamic Task Sampling using LLM-generated su…

We explore the automatic generation of interactive, scenario-based lessons designed to train novice human tutors who teach middle school mathematics online. Employing prompt engineering through a Retrieval-Augmented Generation approach with…

Large language models (LLMs) offer significant promise as a knowledge source for task learning. Prompt engineering has been shown to be effective for eliciting knowledge from an LLM, but alone it is insufficient for acquiring relevant,…

Reinforcement learning struggles in the face of long-horizon tasks and sparse goals due to the difficulty in manual reward specification. While existing methods address this by adding intrinsic rewards, they may fail to provide meaningful…

Collecting large amounts of real-world interaction data to train general robotic policies is often prohibitively expensive, thus motivating the use of simulation data. However, existing methods for data generation have generally focused on…

Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a novel agent capability that can construct cues (or…

We explore the use of GPT-4 on a humanoid robot in simulation and the real world as proof of concept of a novel large language model (LLM) driven behaviour method. LLMs have shown the ability to perform various tasks, including robotic…

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous…

The emergence of Large Language Models (LLMs) in Multi-Agent Systems (MAS) has opened new possibilities for artificial intelligence, yet current implementations face significant challenges in resource management, task coordination, and…

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods manually parse tool documentation and create in-context…

Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments…

Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually…

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually…

Recently, the emergence of large language models (LLMs) has motivated integrating language descriptions into graphs, forming text-attributed graphs (TAGs) that enhance model encoding capabilities from a data-centric perspective. A review of…

Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM…

Many Reinforcement Learning (RL) approaches use joint control signals (positions, velocities, torques) as action space for continuous control tasks. We propose to lift the action space to a higher level in the form of subgoals for a motion…

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoals to a lower level has been shown to enable fast learning…

The landscape of education is changing rapidly, shaped by emerging pedagogical approaches, technological innovations such as artificial intelligence (AI), and evolving societal expectations, all of which demand thorough evaluation of new…

Meta-reinforcement learning (meta-RL) acquires meta-policies that show good performance for tasks in a wide task distribution. However, conventional meta-RL, which learns meta-policies by randomly sampling tasks, has been reported to show…

Large Language Models (LLMs) have demonstrated remarkable capabilities for reinforcement learning (RL) models, such as planning and reasoning capabilities. However, the problems of LLMs and RL model collaboration still need to be solved. In…

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However,…