Related papers: Kintsugi: Learning Policies by Repairing Executabl…

Large Language Models (LLMs) have emerged as a new paradigm for embodied reasoning and control, most recently by generating robot policy code that utilizes a custom library of vision and control primitive skills. However, prior arts fix…

Finetuning provides a scalable and cost-effective means of customizing language models for specific tasks or response styles, with greater reliability than prompting or in-context learning. In contrast, the conventional wisdom is that…

While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as understanding object permanence or planning household…

Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific models, causing edited…

We present a new approach to the problems of evaluating and learning personalized decision policies from observational data of past contexts, decisions, and outcomes. Only the outcome of the enacted decision is available and the historical…

Knowledge Graph Embedding (KGE) techniques are crucial in learning compact representations of entities and relations within a knowledge graph, facilitating efficient reasoning and knowledge discovery. While existing methods typically focus…

This paper studies the performative policy learning problem, where agents adjust their features in response to a released policy to improve their potential outcomes, inducing an endogenous distribution shift. There has been growing interest…

Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to…

COVID-19 has impacted nations differently based on their policy implementations. The effective policy requires taking into account public information and adaptability to new knowledge. Epidemiological models built to understand COVID-19…

This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable settings that unifies Perception, Knowledge, and Policy. The…

Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph.Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering…

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…

Many Knowledege Graphs (KGs) are frequently updated, forcing their Knowledge Graph Embeddings (KGEs) to adapt to these changes. To address this problem, continual learning techniques for KGEs incorporate embeddings for new entities while…

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…

Many AI applications rely on knowledge about a relevant real-world domain that is encoded by means of some logical knowledge base (KB). The most essential benefit of logical KBs is the opportunity to perform automatic reasoning to derive…

Cross-robot policy learning -- training a single policy to perform well across multiple embodiments -- remains a central challenge in robot learning. Transformer-based policies, such as vision-language-action (VLA) models, are typically…

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt…

Modernizing legacy software systems is a critical but challenging task, often hampered by a lack of documentation and understanding of the original system's intricate decision logic. Traditional approaches like behavioral cloning merely…

An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…

Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of…