Timezone: »

 
Poster
MobILE: Model-Based Imitation Learning From Observation Alone
Rahul Kidambi · Jonathan Chang · Wen Sun

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @
in Poster Session 4 »

This paper studies Imitation Learning from Observations alone (ILFO) where the learner is presented with expert demonstrations that consist only of states visited by an expert (without access to actions taken by the expert). We present a provably efficient model-based framework MobILE to solve the ILFO problem. MobILE involves carefully trading off exploration against imitation - this is achieved by integrating the idea of optimism in the face of uncertainty into the distribution matching imitation learning (IL) framework. We provide a unified analysis for MobILE, and demonstrate that MobILE enjoys strong performance guarantees for classes of MDP dynamics that satisfy certain well studied notions of complexity. We also show that the ILFO problem is strictly harder than the standard IL problem by reducing ILFO to a multi-armed bandit problem indicating that exploration is necessary for solving ILFO efficiently. We complement these theoretical results with experimental simulations on benchmark OpenAI Gym tasks that indicate the efficacy of MobILE. Code for implementing the MobILE framework is available at https://github.com/rahulkidambi/MobILE-NeurIPS2021.

Keywords: Theory · Reinforcement Learning and Planning · Bandits

Author Information

Rahul Kidambi (Amazon Search & AI)
Jonathan Chang (Cornell University)
Wen Sun (Cornell University)

More from the Same Authors