State Alignment-based Imitation Learning

11/21/2019
by   Fangchen Liu, et al.
0

Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based imitation learning method to train the imitator to follow the state sequences in expert demonstrations as much as possible. The state alignment comes from both local and global perspectives and we combine them into a reinforcement learning framework by a regularized policy update objective. We show the superiority of our method on standard imitation learning settings and imitation learning settings where the expert and imitator have different dynamics models.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

08/10/2021

Imitation Learning by Reinforcement Learning

Imitation Learning algorithms learn a policy from demonstrations of expe...
02/04/2022

SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching

We propose State Matching Offline DIstribution Correction Estimation (SM...
01/08/2020

The Past and Present of Imitation Learning: A Citation Chain Study

Imitation Learning is a promising area of active research. Over the last...
10/20/2020

Robust Imitation Learning from Noisy Demonstrations

Learning from noisy demonstrations is a practical but highly challenging...
04/07/2020

State-Only Imitation Learning for Dexterous Manipulation

Dexterous manipulation has been a long-standing challenge in robotics. R...
07/09/2019

Ranking-Based Reward Extrapolation without Rankings

The performance of imitation learning is typically upper-bounded by the ...
03/04/2022

Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization

Recent progress in state-only imitation learning extends the scope of ap...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.