A Goyal, Y Bengio - Proceedings of the Royal Society A, 2022 - royalsocietypublishing.org
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopaedic list of heuristics). If that hypothesis was correct, we …
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent …
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state …
In this work, we present a scalable reinforcement learning method for training multi-task policies from large offline datasets that can leverage both human demonstrations and …
We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research in scalable robot learning. BridgeData V2 contains 53,896 …
Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of …
J Ji, T Qiu, B Chen, B Zhang, H Lou, K Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, the potential large-scale risks associated with misaligned AI …
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built …
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It …