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, code, and data are available at https://yunhaifeng.com/FOWM .

翻译：强化学习（RL）因数据效率低下而著称，这使得在真实机器人上进行训练变得困难。尽管基于模型的强化学习算法（世界模型）在一定程度上提高了数据效率，但仍需要数小时或数天的交互来学习技能。近年来，离线强化学习被提出作为一种框架，可在无需任何在线交互的情况下，利用预存在的数据集训练强化学习策略。然而，将算法约束在固定数据集上会导致训练与推理之间的状态-动作分布偏移，并限制其在新任务上的适用性。在本工作中，我们试图兼顾两者优势：考虑利用真实机器人上收集的离线数据预训练世界模型，然后通过使用学习到的模型进行规划来收集在线数据，并对模型进行微调。为缓解在线交互过程中的外推误差，我们提出在测试时通过平衡估计回报与（认知）模型不确定性来正则化规划器。我们在仿真环境和真实机器人上对多种视觉-运动控制任务进行了评估，发现即使离线数据有限，我们的方法也能实现对已知和未知任务的少样本微调。视频、代码和数据可通过 https://yunhaifeng.com/FOWM 获取。