A comprehensive survey on pretrained foundation models: A history from bert to chatgpt
Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks with different data modalities. A PFM (eg, BERT, ChatGPT, and GPT-4) is …
downstream tasks with different data modalities. A PFM (eg, BERT, ChatGPT, and GPT-4) is …
A survey on data‐efficient algorithms in big data era
A Adadi - Journal of Big Data, 2021 - Springer
The leading approaches in Machine Learning are notoriously data-hungry. Unfortunately,
many application domains do not have access to big data because acquiring data involves a …
many application domains do not have access to big data because acquiring data involves a …
Mastering diverse domains through world models
Developing a general algorithm that learns to solve tasks across a wide range of
applications has been a fundamental challenge in artificial intelligence. Although current …
applications has been a fundamental challenge in artificial intelligence. Although current …
Deep reinforcement learning at the edge of the statistical precipice
Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing
their relative performance on a large suite of tasks. Most published results on deep RL …
their relative performance on a large suite of tasks. Most published results on deep RL …
The primacy bias in deep reinforcement learning
This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a
tendency to rely on early interactions and ignore useful evidence encountered later …
tendency to rely on early interactions and ignore useful evidence encountered later …
Bigger, better, faster: Human-level atari with human-level efficiency
We introduce a value-based RL agent, which we call BBF, that achieves super-human
performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used …
performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used …
Gaia-1: A generative world model for autonomous driving
Autonomous driving promises transformative improvements to transportation, but building
systems capable of safely navigating the unstructured complexity of real-world scenarios …
systems capable of safely navigating the unstructured complexity of real-world scenarios …
Mastering visual continuous control: Improved data-augmented reinforcement learning
We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual
continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data …
continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data …
Masked world models for visual control
Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient
robot learning from visual observations. Yet the current approaches typically train a single …
robot learning from visual observations. Yet the current approaches typically train a single …
Reinforcement learning with action-free pre-training from videos
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 …
vision domains by learning useful representations for multiple downstream tasks. In this …