DeepAI AI Chat
Log In Sign Up

ADAIL: Adaptive Adversarial Imitation Learning

08/23/2020
by   Yiren Lu, et al.
Google
8

We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single source domain. This is an important problem in robotic learning because in real world scenarios 1) reward functions are hard to obtain, 2) learned policies from one domain are difficult to deploy in another due to varying source to target domain statistics, 3) collecting expert demonstrations in multiple environments where the dynamics are known and controlled is often infeasible. We address these constraints by building upon recent advances in adversarial imitation learning; we condition our policy on a learned dynamics embedding and we employ a domain-adversarial loss to learn a dynamics-invariant discriminator. The effectiveness of our method is demonstrated on simulated control tasks with varying environment dynamics and the learned adaptive agent outperforms several recent baselines.

READ FULL TEXT

page 6

page 7

page 8

page 13

03/10/2021

Learning from Imperfect Demonstrations from Agents with Varying Dynamics

Imitation learning enables robots to learn from demonstrations. Previous...
06/19/2022

Robust Imitation Learning against Variations in Environment Dynamics

In this paper, we propose a robust imitation learning (IL) framework tha...
02/12/2022

Robust Learning from Observation with Model Misspecification

Imitation learning (IL) is a popular paradigm for training policies in r...
11/13/2022

Out-of-Dynamics Imitation Learning from Multimodal Demonstrations

Existing imitation learning works mainly assume that the demonstrator wh...
06/02/2020

Cross-Domain Imitation Learning with a Dual Structure

In this paper, we consider cross-domain imitation learning (CDIL) in whi...
09/16/2022

Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations

Multimodal demonstrations provide robots with an abundance of informatio...
04/12/2019

Few-Shot Bayesian Imitation Learning with Logic over Programs

We describe an expressive class of policies that can be efficiently lear...