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

In reinforcement learning, we typically refer to unsupervised pre-training when we aim to pre-train a policy without a priori access to the task specification, i.e. rewards, to be later employed for efficient learning of downstream tasks.…

Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning; sometimes by many orders of magnitude. This can be detrimental to learning speed and…

Modern machine learning tasks often require considering not just one but multiple objectives. For example, besides the prediction quality, this could be the efficiency, robustness or fairness of the learned models, or any of their…

Inspired by the success of transfer learning in computer vision, roboticists have investigated visual pre-training as a means to improve the learning efficiency and generalization ability of policies learned from pixels. To that end, past…

As machine learning becomes increasingly central to molecular design, it is vital to ensure the reliability of learnable protein-ligand scoring functions on novel protein targets. While many scoring functions perform well on standard…

Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation…

To obtain a language model for a target domain (e.g. math), the current paradigm is to pre-train on a vast amount of generic web text and then fine-tune on the relatively limited amount of target data. Typically, generic data is only mixed…

Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language…

Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…

Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific…

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning…

Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation encourages transfer…

Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific…

Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained…

Reinforcement learning agents must generalize beyond their training experience. Prior work has focused mostly on identical training and evaluation environments. Starting from the recently introduced Crafter benchmark, a 2D open world…

ImageNet pre-training has been regarded as essential for training accurate object detectors for a long time. Recently, it has been shown that object detectors trained from randomly initialized weights can be on par with those fine-tuned…

Humans can flexibly generalize knowledge across domains by leveraging structured relational representations. While prior research has shown how such representations support analogical reasoning, less is known about how they are recruited to…

Recent advancements in large language models (LLMs) have expanded their capabilities beyond traditional text-based tasks to multimodal domains, integrating visual, auditory, and textual data. While multimodal LLMs have been extensively…

In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL…

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…