Timezone: »

 
Poster
Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage
Jonathan Chang · Masatoshi Uehara · Dhruv Sreenivas · Rahul Kidambi · Wen Sun

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
in Poster Session 6 »

This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert demonstrator without additional online environment interactions. Instead, the learner is presented with a static offline dataset of state-action-next state triples from a potentially less proficient behavior policy. We introduce Model-based IL from Offline data (MILO): an algorithmic framework that utilizes the static dataset to solve the offline IL problem efficiently both in theory and in practice. In theory, even if the behavior policy is highly sub-optimal compared to the expert, we show that as long as the data from the behavior policy provides sufficient coverage on the expert state-action traces (and with no necessity for a global coverage over the entire state-action space), MILO can provably combat the covariate shift issue in IL. Complementing our theory results, we also demonstrate that a practical implementation of our approach mitigates covariate shift on benchmark MuJoCo continuous control tasks. We demonstrate that with behavior policies whose performances are less than half of that of the expert, MILO still successfully imitates with an extremely low number of expert state-action pairs while traditional offline IL methods such as behavior cloning (BC) fail completely. Source code is provided at https://github.com/jdchang1/milo.

Keywords: Theory · Reinforcement Learning and Planning

Author Information

Jonathan Chang (Cornell University)
Masatoshi Uehara (Cornell University)
Dhruv Sreenivas (Cornell University)
Rahul Kidambi (Amazon Search & AI)
Wen Sun (Cornell University)

More from the Same Authors