Robust Maximum Entropy Behavior Cloning

01/04/2021
by   Mostafa Hussein, et al.
0

Imitation learning (IL) algorithms use expert demonstrations to learn a specific task. Most of the existing approaches assume that all expert demonstrations are reliable and trustworthy, but what if there exist some adversarial demonstrations among the given data-set? This may result in poor decision-making performance. We propose a novel general frame-work to directly generate a policy from demonstrations that autonomously detect the adversarial demonstrations and exclude them from the data set. At the same time, it's sample, time-efficient, and does not require a simulator. To model such adversarial demonstration we propose a min-max problem that leverages the entropy of the model to assign weights for each demonstration. This allows us to learn the behavior using only the correct demonstrations or a mixture of correct demonstrations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2019

Imitation Learning from Imperfect Demonstration

Imitation learning (IL) aims to learn an optimal policy from demonstrati...
research
05/04/2016

A Bayesian Approach to Policy Recognition and State Representation Learning

Learning from demonstration (LfD) is the process of building behavioral ...
research
12/20/2021

Demonstration Informed Specification Search

This paper considers the problem of learning history dependent task spec...
research
02/03/2020

Elaborating on Learned Demonstrations with Temporal Logic Specifications

Most current methods for learning from demonstrations assume that those ...
research
02/07/2022

Learning from Imperfect Demonstrations via Adversarial Confidence Transfer

Existing learning from demonstration algorithms usually assume access to...
research
03/09/2022

Learning to control from expert demonstrations

In this paper, we revisit the problem of learning a stabilizing controll...
research
12/07/2022

ICT4S2022 – Demonstrations and Posters Track Proceedings

Submissions accepted for The 8th International Conference on ICT for Sus...

Please sign up or login with your details

Forgot password? Click here to reset