Search Results for author: Mitsuhiko Nakamoto

Found 2 papers, 2 papers with code

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

1 code implementation9 Mar 2023 Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine

Our approach, calibrated Q-learning (Cal-QL) accomplishes this by learning a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q-values are at a reasonable scale.

Offline RL Q-Learning +1

Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials

1 code implementation11 Oct 2022 Aviral Kumar, Anikait Singh, Frederik Ebert, Mitsuhiko Nakamoto, Yanlai Yang, Chelsea Finn, Sergey Levine

To our knowledge, PTR is the first RL method that succeeds at learning new tasks in a new domain on a real WidowX robot with as few as 10 task demonstrations, by effectively leveraging an existing dataset of diverse multi-task robot data collected in a variety of toy kitchens.

Offline RL Q-Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.