Saved in:
Bibliographic Details
Main Authors: Ramos, João A. Cândido, Blondé, Lionel, Takeishi, Naoya, Kalousis, Alexandros
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.09805
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911184220848128
author Ramos, João A. Cândido
Blondé, Lionel
Takeishi, Naoya
Kalousis, Alexandros
author_facet Ramos, João A. Cândido
Blondé, Lionel
Takeishi, Naoya
Kalousis, Alexandros
contents In this paper, we introduce MAAD, a novel, sample-efficient on-policy algorithm for Imitation Learning from Observations. MAAD utilizes a surrogate reward signal, which can be derived from various sources such as adversarial games, trajectory matching objectives, or optimal transport criteria. To compensate for the non-availability of expert actions, we rely on an inverse dynamics model that infers plausible actions distribution given the expert's state-state transitions; we regularize the imitator's policy by aligning it to the inferred action distribution. MAAD leads to significantly improved sample efficiency and stability. We demonstrate its effectiveness in a number of MuJoCo environments, both int the OpenAI Gym and the DeepMind Control Suite. We show that it requires considerable fewer interactions to achieve expert performance, outperforming current state-of-the-art on-policy methods. Remarkably, MAAD often stands out as the sole method capable of attaining expert performance levels, underscoring its simplicity and efficacy.
format Preprint
id arxiv_https___arxiv_org_abs_2306_09805
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Mimicking Better by Matching the Approximate Action Distribution
Ramos, João A. Cândido
Blondé, Lionel
Takeishi, Naoya
Kalousis, Alexandros
Machine Learning
In this paper, we introduce MAAD, a novel, sample-efficient on-policy algorithm for Imitation Learning from Observations. MAAD utilizes a surrogate reward signal, which can be derived from various sources such as adversarial games, trajectory matching objectives, or optimal transport criteria. To compensate for the non-availability of expert actions, we rely on an inverse dynamics model that infers plausible actions distribution given the expert's state-state transitions; we regularize the imitator's policy by aligning it to the inferred action distribution. MAAD leads to significantly improved sample efficiency and stability. We demonstrate its effectiveness in a number of MuJoCo environments, both int the OpenAI Gym and the DeepMind Control Suite. We show that it requires considerable fewer interactions to achieve expert performance, outperforming current state-of-the-art on-policy methods. Remarkably, MAAD often stands out as the sole method capable of attaining expert performance levels, underscoring its simplicity and efficacy.
title Mimicking Better by Matching the Approximate Action Distribution
topic Machine Learning
url https://arxiv.org/abs/2306.09805