Learning Shared Safety Constraints from Multi-task Demonstrations

Published: 20 Jun 2023, Last Modified: 10 Jul 2023ILHF Workshop ICML 2023EveryoneRevisions
Keywords: imitation learning, safe reinforcement learning, constraint learning
TL;DR: We learn safety constraints from multi-task demonstrations.
Abstract: Regardless of the particular task we want them to perform in an environment, there are often shared *safety constraints* we want our agents to respect. For example, regardless of whether it is making a sandwich or clearing the table, a kitchen robot should not break a plate. Manually specifying such a constraint can be both time-consuming and error-prone. We show how to learn constraints from expert demonstrations of safe task completion by extending inverse reinforcement learning (IRL) techniques to the space of constraints. Intuitively, we learn constraints that forbid highly rewarding behavior that the expert could have taken but chose not to. Unfortunately, the constraint learning problem is rather ill-posed and typically leads to overly conservative constraints that forbid all behavior that the expert did not take. We counter this by leveraging diverse demonstrations that naturally occur in multi-task settings to learn a tighter set of constraints. We validate our method with simulation experiments on high-dimensional continuous control tasks.
Submission Number: 24
Loading