相关论文: Executive Function: A Contrastive Value Policy for…

Reward design in reinforcement learning and optimal control is challenging. Preference-based alignment addresses this by enabling agents to learn rewards from ranked trajectory pairs provided by humans. However, existing methods often…

Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the…

We develop a novel approach to conformal prediction when the target task has limited data available for training. Conformal prediction identifies a small set of promising output candidates in place of a single prediction, with guarantees…

Many reinforcement learning algorithms use value functions to guide the search for better policies. These methods estimate the value of a single policy while generalizing across many states. The core idea of this paper is to flip this…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Planning and Learning are complementary approaches. Planning relies on deliberative reasoning about the current state and sequence of future reachable states to solve the problem. Learning, on the other hand, is focused on improving system…

Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional memory-based approaches often overfit to limited samples,…

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify…

The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to…

This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples. A common problem setting in few-shot classification assumes random sampling strategy in acquiring data labels, which is…

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

Pre-trained masked language models successfully perform few-shot learning by formulating downstream tasks as text infilling. However, as a strong alternative in full-shot settings, discriminative pre-trained models like ELECTRA do not fit…

Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced.…

In few-shot learning, typically, the loss function which is applied at test time is the one we are ultimately interested in minimising, such as the mean-squared-error loss for a regression problem. However, given that we have few samples at…

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…

This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that…

Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is…

Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments,…

Recent work on few-shot learning \cite{tian2020rethinking} showed that quality of learned representations plays an important role in few-shot classification performance. On the other hand, the goal of self-supervised learning is to recover…