Description
General-purpose robotic systems must understand a large repertoire of skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to acquire each skill makes the prospect of a generalist robot trained with RL daunting. In MT-Opt, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks. By leveraging the dataset, we demonstrate how MT-Opt can learn a wide range of skills, including semantic picking (i.e., picking an object from a particular category), placing into various fixtures (e.g., placing a food item onto a plate), covering, aligning, and rearranging. We train and evaluate our system on a set of 12 real-world tasks with data collected from 7 robots, and demonstrate the performance of our system both in terms of its ability to generalize to structurally similar new tasks, and acquire distinct new tasks more quickly by leveraging past experience.
The MT-Opt dataset has ~1M RL trajectories and ~0.5M images used to train the MT-Opt Q function and the success detector used in the MT-Opt publication. Check out our blog post for more information.