相关论文: A Minimalist Prompt for Zero-Shot Policy Learning

Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset…

Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each…

The field of machine learning has recently made significant progress in reducing the requirements for labelled training data when building new models. These `cheaper' learning techniques hold significant potential for the social sciences,…

Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…

The remarkable advancements in large language models (LLMs) have brought about significant improvements in Natural Language Processing(NLP) tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on…

In reinforcement learning (RL), an agent learns to perform a task by interacting with an environment and receiving feedback (a numerical reward) for its actions. However, the assumption that rewards are always observable is often not…

Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workpieces so that building predictive models which can…

Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples…

One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this challenge by either…

Reinforcement learning (RL) approaches based on Markov Decision Processes (MDPs) are predominantly applied in the robot joint space, often relying on limited task-specific information and partial awareness of the 3D environment. In…

Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. However, how to select new tasks to improve the performance and…

Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test…

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state…

Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that…

As general purpose robots become more capable, pre-programming of all tasks at the factory will become less practical. We would like for non-technical human owners to be able to communicate, through interaction with their robot, the details…

Meta learning has attracted much attention recently in machine learning community. Contrary to conventional machine learning aiming to learn inherent prediction rules to predict labels for new query data, meta learning aims to learn the…

Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called…

It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. This motivates much of the recent theoretical study on linear MDPs. However, most approaches require a given…

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data. While prompting has emerged as a promising paradigm for few-shot and zero-shot learning, it is often…

When adapting large language models (LLMs) to a specific downstream task, two primary approaches are commonly employed: (1) prompt engineering, often with in-context few-shot learning, leveraging the model's inherent generalization…