Of Moments and Matching: Trade-offs and Treatments in Imitation Learning

03/04/2021
by   Gokul Swamy, et al.
0

We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching. At its core, our classification scheme is based on whether the learner attempts to match (1) reward or (2) action-value moments of the expert's behavior, with each option leading to differing algorithmic approaches. By considering adversarially chosen divergences between learner and expert behavior, we are able to derive bounds on policy performance that apply for all algorithms in each of these classes, the first to our knowledge. We also introduce the notion of recoverability, implicit in many previous analyses of imitation learning, which allows us to cleanly delineate how well each algorithmic family is able to mitigate compounding errors. We derive two novel algorithm templates, AdVIL and AdRIL, with strong guarantees, simple implementation, and competitive empirical performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/19/2018

Global overview of Imitation Learning

Imitation Learning is a sequential task where the learner tries to mimic...
research
08/03/2022

Sequence Model Imitation Learning with Unobserved Contexts

We consider imitation learning problems where the expert has access to a...
research
08/04/2021

A Pragmatic Look at Deep Imitation Learning

The introduction of the generative adversarial imitation learning (GAIL)...
research
06/23/2014

Reinforcement and Imitation Learning via Interactive No-Regret Learning

Recent work has demonstrated that problems-- particularly imitation lear...
research
03/03/2023

How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement

Imitation learning aims to mimic the behavior of experts without explici...
research
02/22/2021

Optimism is All You Need: Model-Based Imitation Learning From Observation Alone

This paper studies Imitation Learning from Observations alone (ILFO) whe...
research
08/31/2018

Imitation Learning for Neural Morphological String Transduction

We employ imitation learning to train a neural transition-based string t...

Please sign up or login with your details

Forgot password? Click here to reset