Domain Adaptive Imitation Learning

Abstract

We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable and RL procedures are expensive. We formalize the Domain Adaptive Imitation Learning (DAIL) problem, which is a unified framework for imitation learning in the presence of viewpoint, embodiment, and dynamics mismatch. Informally, DAIL is the process of learning how to perform a task optimally, given demonstrations of the task in a distinct domain. We propose a two step approach to DAIL: alignment followed by adaptation. In the alignment step we execute a novel unsupervised MDP alignment algorithm, Generative Adversarial MDP Alignment (GAMA), to learn state and action correspondences from \emph{unpaired, unaligned} demonstrations. In the adaptation step we leverage the correspondences to zero-shot imitate tasks across domains. To describe when DAIL is feasible via alignment and adaptation, we introduce a theory of MDP alignability. We experimentally evaluate GAMA against baselines in embodiment, viewpoint, and dynamics mismatch scenarios where aligned demonstrations don't exist and show the effectiveness of our approach.

arXiv commentICML 2020

Cited by in corpus (8)

• XIRL: Cross-embodiment Inverse Reinforcement Learning
• Reinforcement Learning with Videos: Combining Offline Observations with Interaction
• Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning
• Cross-Domain Imitation Learning via Optimal Transport
• Cross-domain Imitation from Observations
• HILONet: Hierarchical Imitation Learning from Non-Aligned Observations
• Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain
• Imitation with Neural Density Models