相关论文: Kintsugi: Learning Policies by Repairing Executabl…

Contemporary GUI agents, while increasingly capable due to advances in Large Vision-Language Models (VLMs), often operate with a critical limitation: they treat each task in isolation, lacking a mechanism to systematically learn from past…

Morphology-aware policy learning is a means of enhancing policy sample efficiency by aggregating data from multiple agents. These types of policies have previously been shown to help generalize over dynamic, kinematic, and limb…

Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that…

Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current…

Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating…

Embodied agents powered by large language models (LLMs), such as Voyager, promise open-ended competence in worlds such as Minecraft. However, when powered by open-weight LLMs they still falter on elementary tasks after domain-specific…

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and…

Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender systems. In real world, knowledge…

Knowledge Graphs (KG) are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and metadata annotation. Regardless of whether they are built manually by domain experts or with…

This effort is focused on examining the behavior of reinforcement learning systems in personalization environments and detailing the differences in policy entropy associated with the type of learning algorithm utilized. We demonstrate that…

We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous…

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Combining such an embedding model with logic rules has recently attracted increasing attention. Most previous attempts made a one-time injection…

Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over…

Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage. Most…

Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound into failure. Common strategies to mitigate this issue involve expanding the training…

Developing efficient software and hardware has never been harder whether it is for a tiny IoT device or an Exascale supercomputer. Apart from the ever growing design and optimization complexity, there exist even more fundamental problems…

Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing facts in the knowledge…

Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly employ expert-agent switching systems to reduce the expert's burden by limitedly selecting the…

Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an…