相关论文: Salience-Invariant Consistent Policy Learning for …

Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades. Yet, deploying RL policies in real-world scenarios presents the crucial challenge of ensuring safety. Traditional safe…

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…

Visual reinforcement learning is appealing for robotics but expensive -- off-policy methods are sample-efficient yet slow; on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster…

Direct policy search serves as one of the workhorses in modern reinforcement learning (RL), and its applications in continuous control tasks have recently attracted increasing attention. In this work, we investigate the convergence theory…

Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However,…

Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this paper, we present…

This paper addresses policy learning in non-stationary environments and games with continuous actions. Rather than the classical reward maximization mechanism, inspired by the ideas of follow-the-regularized-leader (FTRL) and mirror descent…

Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor…

Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. Such methods enable agents to learn complex tasks from humans that are…

Parallel Continual Learning (PCL) tasks investigate the training methods for continual learning with multi-source input, where data from different tasks are learned as they arrive. PCL offers high training efficiency and is well-suited for…

Computational imaging has been revolutionized by compressed sensing algorithms, which offer guaranteed uniqueness, convergence, and stability properties. Model-based deep learning methods that combine imaging physics with learned…

Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and…

Continual learning (CL) is under-explored in the video domain. The few existing works contain splits with imbalanced class distributions over the tasks, or study the problem in unsuitable datasets. We introduce vCLIMB, a novel video…

This paper introduces ACTLLM (Action Consistency Tuned Large Language Model), a novel approach for robot manipulation in dynamic environments. Traditional vision-based systems often struggle to learn visual representations that excel in…

Event-based camera has emerged as a promising paradigm for robot perception, offering advantages with high temporal resolution, high dynamic range, and robustness to motion blur. However, existing deep learning-based event processing…

Data-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations. Although a number of imagebased salient object and fixation detection models have been…

Recent advances in zero-shot learning (ZSL) have demonstrated the potential of generative models. Typically, generative ZSL synthesizes visual features conditioned on semantic prototypes to model the data distribution of unseen classes,…

Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by…

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must…

We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gradient descent…