Ryan Julian

TL;DR: An open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks is proposed to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks.

TL;DR: It is shown how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally extended instructions, while value functions associated with these skills provide the grounding necessary to connect this knowledge to a particular physical environment.

TL;DR: In this article, a scale indicative of actual gesture distance traversed in performance of the gesture is identified, and a movement or action is displayed on the device based, at least in part, on a ratio between the identified scale and the scale of the displayed movement.

TL;DR: In this article, the authors propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks, and evaluate 7 state-of-the-art meta-learner algorithms on these tasks.

TL;DR: In this article , the authors present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties and verify their conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size and data diversity based on a large-scale data collection on real robots performing real-world tasks.