Search Results for author:
Found 2 papers, 2 papers with code
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
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.
Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
