相关论文: Investigating Pre-Training Objectives for Generali…

Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled…

Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…

The ratio of outlier parameters in language pre-training models and vision pre-training models differs significantly, making cross-modality (language and vision) inherently more challenging than cross-domain adaptation. As a result, many…

Averaging checkpoints along the training trajectory is a simple yet powerful approach to improve the generalization performance of Machine Learning models and reduce training time. Motivated by these potential gains, and in an effort to…

The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

In Audio-Visual Navigation (AVN), agents must locate sound sources in unseen 3D environments using visual and auditory cues. However, existing methods often struggle with generalization in unseen scenarios, as they tend to overfit to…

As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibility, and fair comparison. Vision agents lack such…

Width-based planning has shown promising results on Atari 2600 games using pixel input, while using substantially fewer environment interactions than reinforcement learning. Recent width-based approaches have computed feature vectors for…

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…

The past decade has seen the rapid development of Reinforcement Learning, which acquires impressive performance with numerous training resources. However, one of the greatest challenges in RL is generalization efficiency (i.e.,…

Learning agile humanoid behaviors from human motion offers a powerful route to natural, coordinated control, but existing approaches face a persistent trade-off: reference-tracking policies are often brittle outside the demonstration…

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate the issue,…

Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT). Unlike GBDT, deep models can additionally benefit from pretraining, which is a workhorse of DL for vision and NLP.…

Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with…

Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each…

We create a novel benchmark for evaluating a Deployable Lifelong Learning system for Visual Reinforcement Learning (RL) that is pretrained on a curated dataset, and propose a novel Scalable Lifelong Learning system capable of retaining…

Representation learning based on multi-task pretraining has become a powerful approach in many domains. In particular, task-aware representation learning aims to learn an optimal representation for a specific target task by sampling data…

Behavior Trees (BTs) provide a structured and reactive framework for decision-making, commonly used to switch between sub-controllers based on environmental conditions. Reinforcement Learning (RL), on the other hand, can learn near-optimal…

When playing video-games we immediately detect which entity we control and we center the attention towards it to focus the learning and reduce its dimensionality. Reinforcement Learning (RL) has been able to deal with big state spaces,…