Finetuning Offline World Models in the Real WorldDownload PDF

Published: 30 Aug 2023, Last Modified: 17 Oct 2023CoRL 2023 OralReaders: Everyone
Keywords: Model-Based Reinforcement Learning, Real-World Robotics
TL;DR: We propose a framework for offline-to-online finetuning of world models and demonstrate its effectiveness in real robot tasks.
Abstract: Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of interaction to learn skills. Recently, offline RL has been proposed as a framework for training RL policies on pre-existing datasets without any online interaction. However, constraining an algorithm to a fixed dataset induces a state-action distribution shift between training and inference, and limits its applicability to new tasks. In this work, we seek to get the best of both worlds: we consider the problem of pretraining a world model with offline data collected on a real robot, and then finetuning the model on online data collected by planning with the learned model. To mitigate extrapolation errors during online interaction, we propose to regularize the planner at test-time by balancing estimated returns and (epistemic) model uncertainty. We evaluate our method on a variety of visuo-motor control tasks in simulation and on a real robot, and find that our method enables few-shot finetuning to seen and unseen tasks even when offline data is limited. Videos are available at
Student First Author: yes
Supplementary Material: zip
Instructions: I have read the instructions for authors (
Publication Agreement: pdf
13 Replies